load_backend: loaded RPC backend from /ggml-rpc.dll ggml_vulkan: Found 2 Vulkan devices: ggml_vulkan: 0 = AMD Radeon(TM) Graphics (AMD proprietary driver) | uma: 1 | fp16: 1 | bf16: 0 | fp4: 0 | warp size: 32 | shared memory: 32768 | int dot: 1 | matrix cores: none ggml_vulkan: 1 = AMD Radeon RX 9070 (AMD proprietary driver) | uma: 0 | fp16: 1 | bf16: 1 | fp4: 0 | warp size: 64 | shared memory: 32768 | int dot: 1 | matrix cores: KHR_coopmat load_backend: loaded Vulkan backend from /ggml-vulkan.dll load_backend: loaded CPU backend from /ggml-cpu-zen4.dll llama_model_loader: loaded meta data with 27 key-value pairs and 443 tensors from /qwen3-14b-q4_k_m.gguf (version GGUF V3 (latest)) llama_model_loader: Dumping metadata keys/values. Note: KV overrides do not apply in this output. llama_model_loader: - kv 0: general.architecture str = qwen3 llama_model_loader: - kv 1: general.type str = model llama_model_loader: - kv 2: general.name str = Qwen3 14B llama_model_loader: - kv 3: general.basename str = Qwen3 llama_model_loader: - kv 4: general.size_label str = 14B llama_model_loader: - kv 5: qwen3.block_count u32 = 40 llama_model_loader: - kv 6: qwen3.context_length u32 = 40960 llama_model_loader: - kv 7: qwen3.embedding_length u32 = 5120 llama_model_loader: - kv 8: qwen3.feed_forward_length u32 = 17408 llama_model_loader: - kv 9: qwen3.attention.head_count u32 = 40 llama_model_loader: - kv 10: qwen3.attention.head_count_kv u32 = 8 llama_model_loader: - kv 11: qwen3.rope.freq_base f32 = 1000000.000000 llama_model_loader: - kv 12: qwen3.attention.layer_norm_rms_epsilon f32 = 0.000001 llama_model_loader: - kv 13: qwen3.attention.key_length u32 = 128 llama_model_loader: - kv 14: qwen3.attention.value_length u32 = 128 llama_model_loader: - kv 15: tokenizer.ggml.model str = gpt2 llama_model_loader: - kv 16: tokenizer.ggml.pre str = qwen2 llama_model_loader: - kv 17: tokenizer.ggml.tokens arr[str,151936] = ["!", "\"", "#", "$", "%", "&", "'", ... llama_model_loader: - kv 18: tokenizer.ggml.token_type arr[i32,151936] = [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, ... llama_model_loader: - kv 19: tokenizer.ggml.merges arr[str,151387] = ["Ġ Ġ", "ĠĠ ĠĠ", "i n", "Ġ t",... llama_model_loader: - kv 20: tokenizer.ggml.eos_token_id u32 = 151645 llama_model_loader: - kv 21: tokenizer.ggml.padding_token_id u32 = 151643 llama_model_loader: - kv 22: tokenizer.ggml.bos_token_id u32 = 151643 llama_model_loader: - kv 23: tokenizer.ggml.add_bos_token bool = false llama_model_loader: - kv 24: tokenizer.chat_template str = {%- if tools %}\n {{- '<|im_start|>... llama_model_loader: - kv 25: general.quantization_version u32 = 2 llama_model_loader: - kv 26: general.file_type u32 = 15 llama_model_loader: - type f32: 161 tensors llama_model_loader: - type f16: 40 tensors llama_model_loader: - type q4_K: 221 tensors llama_model_loader: - type q6_K: 21 tensors print_info: file format = GGUF V3 (latest) print_info: file type = Q4_K - Medium print_info: file size = 8.63 GiB (5.02 BPW) llama_prepare_model_devices: using device Vulkan1 (AMD Radeon RX 9070) (unknown id) - 15416 MiB free init_tokenizer: initializing tokenizer for type 2 load: 0 unused tokens load: control token: 151661 '<|fim_suffix|>' is not marked as EOG load: control token: 151649 '<|box_end|>' is not marked as EOG load: control token: 151647 '<|object_ref_end|>' is not marked as EOG load: control token: 151654 '<|vision_pad|>' is not marked as EOG load: control token: 151659 '<|fim_prefix|>' is not marked as EOG load: control token: 151648 '<|box_start|>' is not marked as EOG load: control-looking token: 128247 '' was not control-type; this is probably a bug in the model. its type will be overridden load: control token: 151644 '<|im_start|>' is not marked as EOG load: control token: 151646 '<|object_ref_start|>' is not marked as EOG load: control token: 151650 '<|quad_start|>' is not marked as EOG load: control token: 151651 '<|quad_end|>' is not marked as EOG load: control token: 151652 '<|vision_start|>' is not marked as EOG load: control token: 151653 '<|vision_end|>' is not marked as EOG load: control token: 151655 '<|image_pad|>' is not marked as EOG load: control token: 151656 '<|video_pad|>' is not marked as EOG load: control token: 151660 '<|fim_middle|>' is not marked as EOG load: printing all EOG tokens: load: - 128247 ('') load: - 151643 ('<|endoftext|>') load: - 151645 ('<|im_end|>') load: - 151662 ('<|fim_pad|>') load: - 151663 ('<|repo_name|>') load: - 151664 ('<|file_sep|>') load: special tokens cache size = 27 load: token to piece cache size = 0.9311 MB print_info: arch = qwen3 print_info: vocab_only = 0 print_info: no_alloc = 0 print_info: n_ctx_train = 40960 print_info: n_embd_inp = 5120 print_info: n_embd = 5120 print_info: n_embd_out = 5120 print_info: n_layer = 40 print_info: n_layer_all = 40 print_info: n_head = 40 print_info: n_head_kv = 8 print_info: n_rot = 128 print_info: n_swa = 0 print_info: is_swa_any = 0 print_info: non_causal_type = 0 print_info: n_embd_head_k = 128 print_info: n_embd_head_v = 128 print_info: n_gqa = 5 print_info: n_embd_k_gqa = 1024 print_info: n_embd_v_gqa = 1024 print_info: f_norm_eps = 0.0e+00 print_info: f_norm_rms_eps = 1.0e-06 print_info: f_clamp_kqv = 0.0e+00 print_info: f_max_alibi_bias = 0.0e+00 print_info: f_logit_scale = 0.0e+00 print_info: f_attn_scale = 0.0e+00 print_info: f_attn_value_scale = 0.0000 print_info: n_ff = 17408 print_info: n_expert = 0 print_info: n_expert_used = 0 print_info: n_expert_groups = 0 print_info: n_group_used = 0 print_info: causal attn = 1 print_info: pooling type = -1 print_info: rope type = 2 print_info: rope scaling = linear print_info: freq_base_train = 1000000.0 print_info: freq_scale_train = 1 print_info: n_ctx_orig_yarn = 40960 print_info: rope_yarn_log_mul = 0.0000 print_info: rope_finetuned = unknown print_info: model type = 14B print_info: model params = 14.77 B print_info: general.name = Qwen3 14B print_info: vocab type = BPE print_info: n_vocab = 151936 print_info: n_merges = 151387 print_info: BOS token = 151643 '<|endoftext|>' print_info: EOS token = 151645 '<|im_end|>' print_info: EOT token = 151645 '<|im_end|>' print_info: PAD token = 151643 '<|endoftext|>' print_info: LF token = 198 'Ċ' print_info: FIM PRE token = 151659 '<|fim_prefix|>' print_info: FIM SUF token = 151661 '<|fim_suffix|>' print_info: FIM MID token = 151660 '<|fim_middle|>' print_info: FIM PAD token = 151662 '<|fim_pad|>' print_info: FIM REP token = 151663 '<|repo_name|>' print_info: FIM SEP token = 151664 '<|file_sep|>' print_info: EOG token = 128247 '' print_info: EOG token = 151643 '<|endoftext|>' print_info: EOG token = 151645 '<|im_end|>' print_info: EOG token = 151662 '<|fim_pad|>' print_info: EOG token = 151663 '<|repo_name|>' print_info: EOG token = 151664 '<|file_sep|>' print_info: max token length = 256 load_tensors: loading model tensors, this can take a while... (load_mode = mmap) load_tensors: layer 0 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 1 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 2 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 3 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 4 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 5 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 6 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 7 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 8 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 9 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 10 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 11 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 12 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 13 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 14 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 15 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 16 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 17 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 18 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 19 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 20 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 21 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 22 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 23 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 24 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 25 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 26 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 27 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 28 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 29 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 30 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 31 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 32 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 33 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 34 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 35 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 36 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 37 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 38 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 39 assigned to device Vulkan1, is_swa = 0 load_tensors: layer 40 assigned to device Vulkan1, is_swa = 0 create_tensor: loading tensor token_embd.weight create_tensor: loading tensor output_norm.weight create_tensor: loading tensor output.weight create_tensor: loading tensor cls.output.weight create_tensor: loading tensor blk.0.attn_norm.weight create_tensor: loading tensor blk.0.attn_qkv.weight create_tensor: loading tensor blk.0.attn_q.weight create_tensor: loading tensor blk.0.attn_k.weight create_tensor: loading tensor blk.0.attn_v.weight create_tensor: loading tensor blk.0.attn_q.bias create_tensor: loading tensor blk.0.attn_k.bias create_tensor: loading tensor blk.0.attn_v.bias create_tensor: loading tensor blk.0.attn_output.weight create_tensor: loading tensor blk.0.attn_k_norm.weight create_tensor: loading tensor blk.0.attn_q_norm.weight create_tensor: loading tensor blk.0.ffn_norm.weight create_tensor: loading tensor blk.0.ffn_gate.weight create_tensor: loading tensor blk.0.ffn_down.weight create_tensor: loading tensor blk.0.ffn_up.weight create_tensor: loading tensor blk.1.attn_norm.weight create_tensor: loading tensor blk.1.attn_qkv.weight create_tensor: loading tensor blk.1.attn_q.weight create_tensor: loading tensor blk.1.attn_k.weight create_tensor: loading tensor blk.1.attn_v.weight create_tensor: loading tensor blk.1.attn_q.bias create_tensor: loading tensor blk.1.attn_k.bias create_tensor: loading tensor blk.1.attn_v.bias create_tensor: loading tensor blk.1.attn_output.weight create_tensor: loading tensor blk.1.attn_k_norm.weight create_tensor: loading tensor blk.1.attn_q_norm.weight create_tensor: loading tensor blk.1.ffn_norm.weight create_tensor: loading tensor blk.1.ffn_gate.weight create_tensor: loading tensor blk.1.ffn_down.weight create_tensor: loading tensor blk.1.ffn_up.weight create_tensor: loading tensor blk.2.attn_norm.weight create_tensor: loading tensor blk.2.attn_qkv.weight create_tensor: loading tensor blk.2.attn_q.weight create_tensor: loading tensor blk.2.attn_k.weight create_tensor: loading tensor blk.2.attn_v.weight create_tensor: loading tensor blk.2.attn_q.bias create_tensor: loading tensor blk.2.attn_k.bias create_tensor: loading tensor blk.2.attn_v.bias create_tensor: loading tensor blk.2.attn_output.weight create_tensor: loading tensor blk.2.attn_k_norm.weight create_tensor: loading tensor blk.2.attn_q_norm.weight create_tensor: loading tensor blk.2.ffn_norm.weight create_tensor: loading tensor blk.2.ffn_gate.weight create_tensor: loading tensor blk.2.ffn_down.weight create_tensor: loading tensor blk.2.ffn_up.weight create_tensor: loading tensor blk.3.attn_norm.weight create_tensor: loading tensor blk.3.attn_qkv.weight create_tensor: loading tensor blk.3.attn_q.weight create_tensor: loading tensor blk.3.attn_k.weight create_tensor: loading tensor blk.3.attn_v.weight create_tensor: loading tensor blk.3.attn_q.bias create_tensor: loading tensor blk.3.attn_k.bias create_tensor: loading tensor blk.3.attn_v.bias create_tensor: loading tensor blk.3.attn_output.weight create_tensor: loading tensor blk.3.attn_k_norm.weight create_tensor: loading tensor blk.3.attn_q_norm.weight create_tensor: loading tensor blk.3.ffn_norm.weight create_tensor: loading tensor blk.3.ffn_gate.weight create_tensor: loading tensor blk.3.ffn_down.weight create_tensor: loading tensor blk.3.ffn_up.weight create_tensor: loading tensor blk.4.attn_norm.weight create_tensor: loading tensor blk.4.attn_qkv.weight create_tensor: loading tensor blk.4.attn_q.weight create_tensor: loading tensor blk.4.attn_k.weight create_tensor: loading tensor blk.4.attn_v.weight create_tensor: loading tensor blk.4.attn_q.bias create_tensor: loading tensor blk.4.attn_k.bias create_tensor: loading tensor blk.4.attn_v.bias create_tensor: loading tensor blk.4.attn_output.weight create_tensor: loading tensor blk.4.attn_k_norm.weight create_tensor: loading tensor blk.4.attn_q_norm.weight create_tensor: loading tensor blk.4.ffn_norm.weight create_tensor: loading tensor blk.4.ffn_gate.weight create_tensor: loading tensor blk.4.ffn_down.weight create_tensor: loading tensor blk.4.ffn_up.weight create_tensor: loading tensor blk.5.attn_norm.weight create_tensor: loading tensor blk.5.attn_qkv.weight create_tensor: loading tensor blk.5.attn_q.weight create_tensor: loading tensor blk.5.attn_k.weight create_tensor: loading tensor blk.5.attn_v.weight create_tensor: loading tensor blk.5.attn_q.bias create_tensor: loading tensor blk.5.attn_k.bias create_tensor: loading tensor blk.5.attn_v.bias create_tensor: loading tensor blk.5.attn_output.weight create_tensor: loading tensor blk.5.attn_k_norm.weight create_tensor: loading tensor blk.5.attn_q_norm.weight create_tensor: loading tensor blk.5.ffn_norm.weight create_tensor: loading tensor blk.5.ffn_gate.weight create_tensor: loading tensor blk.5.ffn_down.weight create_tensor: loading tensor blk.5.ffn_up.weight create_tensor: loading tensor blk.6.attn_norm.weight create_tensor: loading tensor blk.6.attn_qkv.weight create_tensor: loading tensor blk.6.attn_q.weight create_tensor: loading tensor blk.6.attn_k.weight create_tensor: loading tensor blk.6.attn_v.weight create_tensor: loading tensor blk.6.attn_q.bias create_tensor: loading tensor blk.6.attn_k.bias create_tensor: loading tensor blk.6.attn_v.bias create_tensor: loading tensor blk.6.attn_output.weight create_tensor: loading tensor blk.6.attn_k_norm.weight create_tensor: loading tensor blk.6.attn_q_norm.weight create_tensor: loading tensor blk.6.ffn_norm.weight create_tensor: loading tensor blk.6.ffn_gate.weight create_tensor: loading tensor blk.6.ffn_down.weight create_tensor: loading tensor blk.6.ffn_up.weight create_tensor: loading tensor blk.7.attn_norm.weight create_tensor: loading tensor blk.7.attn_qkv.weight create_tensor: loading tensor blk.7.attn_q.weight create_tensor: loading tensor blk.7.attn_k.weight create_tensor: loading tensor blk.7.attn_v.weight create_tensor: loading tensor blk.7.attn_q.bias create_tensor: loading tensor blk.7.attn_k.bias create_tensor: loading tensor blk.7.attn_v.bias create_tensor: loading tensor blk.7.attn_output.weight create_tensor: loading tensor blk.7.attn_k_norm.weight create_tensor: loading tensor blk.7.attn_q_norm.weight create_tensor: loading tensor blk.7.ffn_norm.weight create_tensor: loading tensor blk.7.ffn_gate.weight create_tensor: loading tensor blk.7.ffn_down.weight create_tensor: loading tensor blk.7.ffn_up.weight create_tensor: loading tensor blk.8.attn_norm.weight create_tensor: loading tensor blk.8.attn_qkv.weight create_tensor: loading tensor blk.8.attn_q.weight create_tensor: loading tensor blk.8.attn_k.weight create_tensor: loading tensor blk.8.attn_v.weight create_tensor: loading tensor blk.8.attn_q.bias create_tensor: loading tensor blk.8.attn_k.bias create_tensor: loading tensor blk.8.attn_v.bias create_tensor: loading tensor blk.8.attn_output.weight create_tensor: loading tensor blk.8.attn_k_norm.weight create_tensor: loading tensor blk.8.attn_q_norm.weight create_tensor: loading tensor blk.8.ffn_norm.weight create_tensor: loading tensor blk.8.ffn_gate.weight create_tensor: loading tensor blk.8.ffn_down.weight create_tensor: loading tensor blk.8.ffn_up.weight create_tensor: loading tensor blk.9.attn_norm.weight create_tensor: loading tensor blk.9.attn_qkv.weight create_tensor: loading tensor blk.9.attn_q.weight create_tensor: loading tensor blk.9.attn_k.weight create_tensor: loading tensor blk.9.attn_v.weight create_tensor: loading tensor blk.9.attn_q.bias create_tensor: loading tensor blk.9.attn_k.bias create_tensor: loading tensor blk.9.attn_v.bias create_tensor: loading tensor blk.9.attn_output.weight create_tensor: loading tensor blk.9.attn_k_norm.weight create_tensor: loading tensor blk.9.attn_q_norm.weight create_tensor: loading tensor blk.9.ffn_norm.weight create_tensor: loading tensor blk.9.ffn_gate.weight create_tensor: loading tensor blk.9.ffn_down.weight create_tensor: loading tensor blk.9.ffn_up.weight create_tensor: loading tensor blk.10.attn_norm.weight create_tensor: loading tensor blk.10.attn_qkv.weight create_tensor: loading tensor blk.10.attn_q.weight create_tensor: loading tensor blk.10.attn_k.weight create_tensor: loading tensor blk.10.attn_v.weight create_tensor: loading tensor blk.10.attn_q.bias create_tensor: loading tensor blk.10.attn_k.bias create_tensor: loading tensor blk.10.attn_v.bias create_tensor: loading tensor blk.10.attn_output.weight create_tensor: loading tensor blk.10.attn_k_norm.weight create_tensor: loading tensor blk.10.attn_q_norm.weight create_tensor: loading tensor blk.10.ffn_norm.weight create_tensor: loading tensor blk.10.ffn_gate.weight create_tensor: loading tensor blk.10.ffn_down.weight create_tensor: loading tensor blk.10.ffn_up.weight create_tensor: loading tensor blk.11.attn_norm.weight create_tensor: loading tensor blk.11.attn_qkv.weight create_tensor: loading tensor blk.11.attn_q.weight create_tensor: loading tensor blk.11.attn_k.weight create_tensor: loading tensor blk.11.attn_v.weight create_tensor: loading tensor blk.11.attn_q.bias create_tensor: loading tensor blk.11.attn_k.bias create_tensor: loading tensor blk.11.attn_v.bias create_tensor: loading tensor blk.11.attn_output.weight create_tensor: loading tensor blk.11.attn_k_norm.weight create_tensor: loading tensor blk.11.attn_q_norm.weight create_tensor: loading tensor blk.11.ffn_norm.weight create_tensor: loading tensor blk.11.ffn_gate.weight create_tensor: loading tensor blk.11.ffn_down.weight create_tensor: loading tensor blk.11.ffn_up.weight create_tensor: loading tensor blk.12.attn_norm.weight create_tensor: loading tensor blk.12.attn_qkv.weight create_tensor: loading tensor blk.12.attn_q.weight create_tensor: loading tensor blk.12.attn_k.weight create_tensor: loading tensor blk.12.attn_v.weight create_tensor: loading tensor blk.12.attn_q.bias create_tensor: loading tensor blk.12.attn_k.bias create_tensor: loading tensor blk.12.attn_v.bias create_tensor: loading tensor blk.12.attn_output.weight create_tensor: loading tensor blk.12.attn_k_norm.weight create_tensor: loading tensor blk.12.attn_q_norm.weight create_tensor: loading tensor blk.12.ffn_norm.weight create_tensor: loading tensor blk.12.ffn_gate.weight create_tensor: loading tensor blk.12.ffn_down.weight create_tensor: loading tensor blk.12.ffn_up.weight create_tensor: loading tensor blk.13.attn_norm.weight create_tensor: loading tensor blk.13.attn_qkv.weight create_tensor: loading tensor blk.13.attn_q.weight create_tensor: loading tensor blk.13.attn_k.weight create_tensor: loading tensor blk.13.attn_v.weight create_tensor: loading tensor blk.13.attn_q.bias create_tensor: loading tensor blk.13.attn_k.bias create_tensor: loading tensor blk.13.attn_v.bias create_tensor: loading tensor blk.13.attn_output.weight create_tensor: loading tensor blk.13.attn_k_norm.weight create_tensor: loading tensor blk.13.attn_q_norm.weight create_tensor: loading tensor blk.13.ffn_norm.weight create_tensor: loading tensor blk.13.ffn_gate.weight create_tensor: loading tensor blk.13.ffn_down.weight create_tensor: loading tensor blk.13.ffn_up.weight create_tensor: loading tensor blk.14.attn_norm.weight create_tensor: loading tensor blk.14.attn_qkv.weight create_tensor: loading tensor blk.14.attn_q.weight create_tensor: loading tensor blk.14.attn_k.weight create_tensor: loading tensor blk.14.attn_v.weight create_tensor: loading tensor blk.14.attn_q.bias create_tensor: loading tensor blk.14.attn_k.bias create_tensor: loading tensor blk.14.attn_v.bias create_tensor: loading tensor blk.14.attn_output.weight create_tensor: loading tensor blk.14.attn_k_norm.weight create_tensor: loading tensor blk.14.attn_q_norm.weight create_tensor: loading tensor blk.14.ffn_norm.weight create_tensor: loading tensor blk.14.ffn_gate.weight create_tensor: loading tensor blk.14.ffn_down.weight create_tensor: loading tensor blk.14.ffn_up.weight create_tensor: loading tensor blk.15.attn_norm.weight create_tensor: loading tensor blk.15.attn_qkv.weight create_tensor: loading tensor blk.15.attn_q.weight create_tensor: loading tensor blk.15.attn_k.weight create_tensor: loading tensor blk.15.attn_v.weight create_tensor: loading tensor blk.15.attn_q.bias create_tensor: loading tensor blk.15.attn_k.bias create_tensor: loading tensor blk.15.attn_v.bias create_tensor: loading tensor blk.15.attn_output.weight create_tensor: loading tensor blk.15.attn_k_norm.weight create_tensor: loading tensor blk.15.attn_q_norm.weight create_tensor: loading tensor blk.15.ffn_norm.weight create_tensor: loading tensor blk.15.ffn_gate.weight create_tensor: loading tensor blk.15.ffn_down.weight create_tensor: loading tensor blk.15.ffn_up.weight create_tensor: loading tensor blk.16.attn_norm.weight create_tensor: loading tensor blk.16.attn_qkv.weight create_tensor: loading tensor blk.16.attn_q.weight create_tensor: loading tensor blk.16.attn_k.weight create_tensor: loading tensor blk.16.attn_v.weight create_tensor: loading tensor blk.16.attn_q.bias create_tensor: loading tensor blk.16.attn_k.bias create_tensor: loading tensor blk.16.attn_v.bias create_tensor: loading tensor blk.16.attn_output.weight create_tensor: loading tensor blk.16.attn_k_norm.weight create_tensor: loading tensor blk.16.attn_q_norm.weight create_tensor: loading tensor blk.16.ffn_norm.weight create_tensor: loading tensor blk.16.ffn_gate.weight create_tensor: loading tensor blk.16.ffn_down.weight create_tensor: loading tensor blk.16.ffn_up.weight create_tensor: loading tensor blk.17.attn_norm.weight create_tensor: loading tensor blk.17.attn_qkv.weight create_tensor: loading tensor blk.17.attn_q.weight create_tensor: loading tensor blk.17.attn_k.weight create_tensor: loading tensor blk.17.attn_v.weight create_tensor: loading tensor blk.17.attn_q.bias create_tensor: loading tensor blk.17.attn_k.bias create_tensor: loading tensor blk.17.attn_v.bias create_tensor: loading tensor blk.17.attn_output.weight create_tensor: loading tensor blk.17.attn_k_norm.weight create_tensor: loading tensor blk.17.attn_q_norm.weight create_tensor: loading tensor blk.17.ffn_norm.weight create_tensor: loading tensor blk.17.ffn_gate.weight create_tensor: loading tensor blk.17.ffn_down.weight create_tensor: loading tensor blk.17.ffn_up.weight create_tensor: loading tensor blk.18.attn_norm.weight create_tensor: loading tensor blk.18.attn_qkv.weight create_tensor: loading tensor blk.18.attn_q.weight create_tensor: loading tensor blk.18.attn_k.weight create_tensor: loading tensor blk.18.attn_v.weight create_tensor: loading tensor blk.18.attn_q.bias create_tensor: loading tensor blk.18.attn_k.bias create_tensor: loading tensor blk.18.attn_v.bias create_tensor: loading tensor blk.18.attn_output.weight create_tensor: loading tensor blk.18.attn_k_norm.weight create_tensor: loading tensor blk.18.attn_q_norm.weight create_tensor: loading tensor blk.18.ffn_norm.weight create_tensor: loading tensor blk.18.ffn_gate.weight create_tensor: loading tensor blk.18.ffn_down.weight create_tensor: loading tensor blk.18.ffn_up.weight create_tensor: loading tensor blk.19.attn_norm.weight create_tensor: loading tensor blk.19.attn_qkv.weight create_tensor: loading tensor blk.19.attn_q.weight create_tensor: loading tensor blk.19.attn_k.weight create_tensor: loading tensor blk.19.attn_v.weight create_tensor: loading tensor blk.19.attn_q.bias create_tensor: loading tensor blk.19.attn_k.bias create_tensor: loading tensor blk.19.attn_v.bias create_tensor: loading tensor blk.19.attn_output.weight create_tensor: loading tensor blk.19.attn_k_norm.weight create_tensor: loading tensor blk.19.attn_q_norm.weight create_tensor: loading tensor blk.19.ffn_norm.weight create_tensor: loading tensor blk.19.ffn_gate.weight create_tensor: loading tensor blk.19.ffn_down.weight create_tensor: loading tensor blk.19.ffn_up.weight create_tensor: loading tensor blk.20.attn_norm.weight create_tensor: loading tensor blk.20.attn_qkv.weight create_tensor: loading tensor blk.20.attn_q.weight create_tensor: loading tensor blk.20.attn_k.weight create_tensor: loading tensor blk.20.attn_v.weight create_tensor: loading tensor blk.20.attn_q.bias create_tensor: loading tensor blk.20.attn_k.bias create_tensor: loading tensor blk.20.attn_v.bias create_tensor: loading tensor blk.20.attn_output.weight create_tensor: loading tensor blk.20.attn_k_norm.weight create_tensor: loading tensor blk.20.attn_q_norm.weight create_tensor: loading tensor blk.20.ffn_norm.weight create_tensor: loading tensor blk.20.ffn_gate.weight create_tensor: loading tensor blk.20.ffn_down.weight create_tensor: loading tensor blk.20.ffn_up.weight create_tensor: loading tensor blk.21.attn_norm.weight create_tensor: loading tensor blk.21.attn_qkv.weight create_tensor: loading tensor blk.21.attn_q.weight create_tensor: loading tensor blk.21.attn_k.weight create_tensor: loading tensor blk.21.attn_v.weight create_tensor: loading tensor blk.21.attn_q.bias create_tensor: loading tensor blk.21.attn_k.bias create_tensor: loading tensor blk.21.attn_v.bias create_tensor: loading tensor blk.21.attn_output.weight create_tensor: loading tensor blk.21.attn_k_norm.weight create_tensor: loading tensor blk.21.attn_q_norm.weight create_tensor: loading tensor blk.21.ffn_norm.weight create_tensor: loading tensor blk.21.ffn_gate.weight create_tensor: loading tensor blk.21.ffn_down.weight create_tensor: loading tensor blk.21.ffn_up.weight create_tensor: loading tensor blk.22.attn_norm.weight create_tensor: loading tensor blk.22.attn_qkv.weight create_tensor: loading tensor blk.22.attn_q.weight create_tensor: loading tensor blk.22.attn_k.weight create_tensor: loading tensor blk.22.attn_v.weight create_tensor: loading tensor blk.22.attn_q.bias create_tensor: loading tensor blk.22.attn_k.bias create_tensor: loading tensor blk.22.attn_v.bias create_tensor: loading tensor blk.22.attn_output.weight create_tensor: loading tensor blk.22.attn_k_norm.weight create_tensor: loading tensor blk.22.attn_q_norm.weight create_tensor: loading tensor blk.22.ffn_norm.weight create_tensor: loading tensor blk.22.ffn_gate.weight create_tensor: loading tensor blk.22.ffn_down.weight create_tensor: loading tensor blk.22.ffn_up.weight create_tensor: loading tensor blk.23.attn_norm.weight create_tensor: loading tensor blk.23.attn_qkv.weight create_tensor: loading tensor blk.23.attn_q.weight create_tensor: loading tensor blk.23.attn_k.weight create_tensor: loading tensor blk.23.attn_v.weight create_tensor: loading tensor blk.23.attn_q.bias create_tensor: loading tensor blk.23.attn_k.bias create_tensor: loading tensor blk.23.attn_v.bias create_tensor: loading tensor blk.23.attn_output.weight create_tensor: loading tensor blk.23.attn_k_norm.weight create_tensor: loading tensor blk.23.attn_q_norm.weight create_tensor: loading tensor blk.23.ffn_norm.weight create_tensor: loading tensor blk.23.ffn_gate.weight create_tensor: loading tensor blk.23.ffn_down.weight create_tensor: loading tensor blk.23.ffn_up.weight create_tensor: loading tensor blk.24.attn_norm.weight create_tensor: loading tensor blk.24.attn_qkv.weight create_tensor: loading tensor blk.24.attn_q.weight create_tensor: loading tensor blk.24.attn_k.weight create_tensor: loading tensor blk.24.attn_v.weight create_tensor: loading tensor blk.24.attn_q.bias create_tensor: loading tensor blk.24.attn_k.bias create_tensor: loading tensor blk.24.attn_v.bias create_tensor: loading tensor blk.24.attn_output.weight create_tensor: loading tensor blk.24.attn_k_norm.weight create_tensor: loading tensor blk.24.attn_q_norm.weight create_tensor: loading tensor blk.24.ffn_norm.weight create_tensor: loading tensor blk.24.ffn_gate.weight create_tensor: loading tensor blk.24.ffn_down.weight create_tensor: loading tensor blk.24.ffn_up.weight create_tensor: loading tensor blk.25.attn_norm.weight create_tensor: loading tensor blk.25.attn_qkv.weight create_tensor: loading tensor blk.25.attn_q.weight create_tensor: loading tensor blk.25.attn_k.weight create_tensor: loading tensor blk.25.attn_v.weight create_tensor: loading tensor blk.25.attn_q.bias create_tensor: loading tensor blk.25.attn_k.bias create_tensor: loading tensor blk.25.attn_v.bias create_tensor: loading tensor blk.25.attn_output.weight create_tensor: loading tensor blk.25.attn_k_norm.weight create_tensor: loading tensor blk.25.attn_q_norm.weight create_tensor: loading tensor blk.25.ffn_norm.weight create_tensor: loading tensor blk.25.ffn_gate.weight create_tensor: loading tensor blk.25.ffn_down.weight create_tensor: loading tensor blk.25.ffn_up.weight create_tensor: loading tensor blk.26.attn_norm.weight create_tensor: loading tensor blk.26.attn_qkv.weight create_tensor: loading tensor blk.26.attn_q.weight create_tensor: loading tensor blk.26.attn_k.weight create_tensor: loading tensor blk.26.attn_v.weight create_tensor: loading tensor blk.26.attn_q.bias create_tensor: loading tensor blk.26.attn_k.bias create_tensor: loading tensor blk.26.attn_v.bias create_tensor: loading tensor blk.26.attn_output.weight create_tensor: loading tensor blk.26.attn_k_norm.weight create_tensor: loading tensor blk.26.attn_q_norm.weight create_tensor: loading tensor blk.26.ffn_norm.weight create_tensor: loading tensor blk.26.ffn_gate.weight create_tensor: loading tensor blk.26.ffn_down.weight create_tensor: loading tensor blk.26.ffn_up.weight create_tensor: loading tensor blk.27.attn_norm.weight create_tensor: loading tensor blk.27.attn_qkv.weight create_tensor: loading tensor blk.27.attn_q.weight create_tensor: loading tensor blk.27.attn_k.weight create_tensor: loading tensor blk.27.attn_v.weight create_tensor: loading tensor blk.27.attn_q.bias create_tensor: loading tensor blk.27.attn_k.bias create_tensor: loading tensor blk.27.attn_v.bias create_tensor: loading tensor blk.27.attn_output.weight create_tensor: loading tensor blk.27.attn_k_norm.weight create_tensor: loading tensor blk.27.attn_q_norm.weight create_tensor: loading tensor blk.27.ffn_norm.weight create_tensor: loading tensor blk.27.ffn_gate.weight create_tensor: loading tensor blk.27.ffn_down.weight create_tensor: loading tensor blk.27.ffn_up.weight create_tensor: loading tensor blk.28.attn_norm.weight create_tensor: loading tensor blk.28.attn_qkv.weight create_tensor: loading tensor blk.28.attn_q.weight create_tensor: loading tensor blk.28.attn_k.weight create_tensor: loading tensor blk.28.attn_v.weight create_tensor: loading tensor blk.28.attn_q.bias create_tensor: loading tensor blk.28.attn_k.bias create_tensor: loading tensor blk.28.attn_v.bias create_tensor: loading tensor blk.28.attn_output.weight create_tensor: loading tensor blk.28.attn_k_norm.weight create_tensor: loading tensor blk.28.attn_q_norm.weight create_tensor: loading tensor blk.28.ffn_norm.weight create_tensor: loading tensor blk.28.ffn_gate.weight create_tensor: loading tensor blk.28.ffn_down.weight create_tensor: loading tensor blk.28.ffn_up.weight create_tensor: loading tensor blk.29.attn_norm.weight create_tensor: loading tensor blk.29.attn_qkv.weight create_tensor: loading tensor blk.29.attn_q.weight create_tensor: loading tensor blk.29.attn_k.weight create_tensor: loading tensor blk.29.attn_v.weight create_tensor: loading tensor blk.29.attn_q.bias create_tensor: loading tensor blk.29.attn_k.bias create_tensor: loading tensor blk.29.attn_v.bias create_tensor: loading tensor blk.29.attn_output.weight create_tensor: loading tensor blk.29.attn_k_norm.weight create_tensor: loading tensor blk.29.attn_q_norm.weight create_tensor: loading tensor blk.29.ffn_norm.weight create_tensor: loading tensor blk.29.ffn_gate.weight create_tensor: loading tensor blk.29.ffn_down.weight create_tensor: loading tensor blk.29.ffn_up.weight create_tensor: loading tensor blk.30.attn_norm.weight create_tensor: loading tensor blk.30.attn_qkv.weight create_tensor: loading tensor blk.30.attn_q.weight create_tensor: loading tensor blk.30.attn_k.weight create_tensor: loading tensor blk.30.attn_v.weight create_tensor: loading tensor blk.30.attn_q.bias create_tensor: loading tensor blk.30.attn_k.bias create_tensor: loading tensor blk.30.attn_v.bias create_tensor: loading tensor blk.30.attn_output.weight create_tensor: loading tensor blk.30.attn_k_norm.weight create_tensor: loading tensor blk.30.attn_q_norm.weight create_tensor: loading tensor blk.30.ffn_norm.weight create_tensor: loading tensor blk.30.ffn_gate.weight create_tensor: loading tensor blk.30.ffn_down.weight create_tensor: loading tensor blk.30.ffn_up.weight create_tensor: loading tensor blk.31.attn_norm.weight create_tensor: loading tensor blk.31.attn_qkv.weight create_tensor: loading tensor blk.31.attn_q.weight create_tensor: loading tensor blk.31.attn_k.weight create_tensor: loading tensor blk.31.attn_v.weight create_tensor: loading tensor blk.31.attn_q.bias create_tensor: loading tensor blk.31.attn_k.bias create_tensor: loading tensor blk.31.attn_v.bias create_tensor: loading tensor blk.31.attn_output.weight create_tensor: loading tensor blk.31.attn_k_norm.weight create_tensor: loading tensor blk.31.attn_q_norm.weight create_tensor: loading tensor blk.31.ffn_norm.weight create_tensor: loading tensor blk.31.ffn_gate.weight create_tensor: loading tensor blk.31.ffn_down.weight create_tensor: loading tensor blk.31.ffn_up.weight create_tensor: loading tensor blk.32.attn_norm.weight create_tensor: loading tensor blk.32.attn_qkv.weight create_tensor: loading tensor blk.32.attn_q.weight create_tensor: loading tensor blk.32.attn_k.weight create_tensor: loading tensor blk.32.attn_v.weight create_tensor: loading tensor blk.32.attn_q.bias create_tensor: loading tensor blk.32.attn_k.bias create_tensor: loading tensor blk.32.attn_v.bias create_tensor: loading tensor blk.32.attn_output.weight create_tensor: loading tensor blk.32.attn_k_norm.weight create_tensor: loading tensor blk.32.attn_q_norm.weight create_tensor: loading tensor blk.32.ffn_norm.weight create_tensor: loading tensor blk.32.ffn_gate.weight create_tensor: loading tensor blk.32.ffn_down.weight create_tensor: loading tensor blk.32.ffn_up.weight create_tensor: loading tensor blk.33.attn_norm.weight create_tensor: loading tensor blk.33.attn_qkv.weight create_tensor: loading tensor blk.33.attn_q.weight create_tensor: loading tensor blk.33.attn_k.weight create_tensor: loading tensor blk.33.attn_v.weight create_tensor: loading tensor blk.33.attn_q.bias create_tensor: loading tensor blk.33.attn_k.bias create_tensor: loading tensor blk.33.attn_v.bias create_tensor: loading tensor blk.33.attn_output.weight create_tensor: loading tensor blk.33.attn_k_norm.weight create_tensor: loading tensor blk.33.attn_q_norm.weight create_tensor: loading tensor blk.33.ffn_norm.weight create_tensor: loading tensor blk.33.ffn_gate.weight create_tensor: loading tensor blk.33.ffn_down.weight create_tensor: loading tensor blk.33.ffn_up.weight create_tensor: loading tensor blk.34.attn_norm.weight create_tensor: loading tensor blk.34.attn_qkv.weight create_tensor: loading tensor blk.34.attn_q.weight create_tensor: loading tensor blk.34.attn_k.weight create_tensor: loading tensor blk.34.attn_v.weight create_tensor: loading tensor blk.34.attn_q.bias create_tensor: loading tensor blk.34.attn_k.bias create_tensor: loading tensor blk.34.attn_v.bias create_tensor: loading tensor blk.34.attn_output.weight create_tensor: loading tensor blk.34.attn_k_norm.weight create_tensor: loading tensor blk.34.attn_q_norm.weight create_tensor: loading tensor blk.34.ffn_norm.weight create_tensor: loading tensor blk.34.ffn_gate.weight create_tensor: loading tensor blk.34.ffn_down.weight create_tensor: loading tensor blk.34.ffn_up.weight create_tensor: loading tensor blk.35.attn_norm.weight create_tensor: loading tensor blk.35.attn_qkv.weight create_tensor: loading tensor blk.35.attn_q.weight create_tensor: loading tensor blk.35.attn_k.weight create_tensor: loading tensor blk.35.attn_v.weight create_tensor: loading tensor blk.35.attn_q.bias create_tensor: loading tensor blk.35.attn_k.bias create_tensor: loading tensor blk.35.attn_v.bias create_tensor: loading tensor blk.35.attn_output.weight create_tensor: loading tensor blk.35.attn_k_norm.weight create_tensor: loading tensor blk.35.attn_q_norm.weight create_tensor: loading tensor blk.35.ffn_norm.weight create_tensor: loading tensor blk.35.ffn_gate.weight create_tensor: loading tensor blk.35.ffn_down.weight create_tensor: loading tensor blk.35.ffn_up.weight create_tensor: loading tensor blk.36.attn_norm.weight create_tensor: loading tensor blk.36.attn_qkv.weight create_tensor: loading tensor blk.36.attn_q.weight create_tensor: loading tensor blk.36.attn_k.weight create_tensor: loading tensor blk.36.attn_v.weight create_tensor: loading tensor blk.36.attn_q.bias create_tensor: loading tensor blk.36.attn_k.bias create_tensor: loading tensor blk.36.attn_v.bias create_tensor: loading tensor blk.36.attn_output.weight create_tensor: loading tensor blk.36.attn_k_norm.weight create_tensor: loading tensor blk.36.attn_q_norm.weight create_tensor: loading tensor blk.36.ffn_norm.weight create_tensor: loading tensor blk.36.ffn_gate.weight create_tensor: loading tensor blk.36.ffn_down.weight create_tensor: loading tensor blk.36.ffn_up.weight create_tensor: loading tensor blk.37.attn_norm.weight create_tensor: loading tensor blk.37.attn_qkv.weight create_tensor: loading tensor blk.37.attn_q.weight create_tensor: loading tensor blk.37.attn_k.weight create_tensor: loading tensor blk.37.attn_v.weight create_tensor: loading tensor blk.37.attn_q.bias create_tensor: loading tensor blk.37.attn_k.bias create_tensor: loading tensor blk.37.attn_v.bias create_tensor: loading tensor blk.37.attn_output.weight create_tensor: loading tensor blk.37.attn_k_norm.weight create_tensor: loading tensor blk.37.attn_q_norm.weight create_tensor: loading tensor blk.37.ffn_norm.weight create_tensor: loading tensor blk.37.ffn_gate.weight create_tensor: loading tensor blk.37.ffn_down.weight create_tensor: loading tensor blk.37.ffn_up.weight create_tensor: loading tensor blk.38.attn_norm.weight create_tensor: loading tensor blk.38.attn_qkv.weight create_tensor: loading tensor blk.38.attn_q.weight create_tensor: loading tensor blk.38.attn_k.weight create_tensor: loading tensor blk.38.attn_v.weight create_tensor: loading tensor blk.38.attn_q.bias create_tensor: loading tensor blk.38.attn_k.bias create_tensor: loading tensor blk.38.attn_v.bias create_tensor: loading tensor blk.38.attn_output.weight create_tensor: loading tensor blk.38.attn_k_norm.weight create_tensor: loading tensor blk.38.attn_q_norm.weight create_tensor: loading tensor blk.38.ffn_norm.weight create_tensor: loading tensor blk.38.ffn_gate.weight create_tensor: loading tensor blk.38.ffn_down.weight create_tensor: loading tensor blk.38.ffn_up.weight create_tensor: loading tensor blk.39.attn_norm.weight create_tensor: loading tensor blk.39.attn_qkv.weight create_tensor: loading tensor blk.39.attn_q.weight create_tensor: loading tensor blk.39.attn_k.weight create_tensor: loading tensor blk.39.attn_v.weight create_tensor: loading tensor blk.39.attn_q.bias create_tensor: loading tensor blk.39.attn_k.bias create_tensor: loading tensor blk.39.attn_v.bias create_tensor: loading tensor blk.39.attn_output.weight create_tensor: loading tensor blk.39.attn_k_norm.weight create_tensor: loading tensor blk.39.attn_q_norm.weight create_tensor: loading tensor blk.39.ffn_norm.weight create_tensor: loading tensor blk.39.ffn_gate.weight create_tensor: loading tensor blk.39.ffn_down.weight create_tensor: loading tensor blk.39.ffn_up.weight create_tensor: loading tensor blk.0.attn_q.scale create_tensor: loading tensor blk.0.attn_k.scale create_tensor: loading tensor blk.0.attn_v.scale create_tensor: loading tensor blk.0.attn_output.scale create_tensor: loading tensor blk.0.ffn_gate.scale create_tensor: loading tensor blk.0.ffn_down.scale create_tensor: loading tensor blk.0.ffn_up.scale create_tensor: loading tensor blk.0.attn_q.input_scale create_tensor: loading tensor blk.0.attn_k.input_scale create_tensor: loading tensor blk.0.attn_v.input_scale create_tensor: loading tensor blk.0.attn_output.input_scale create_tensor: loading tensor blk.0.ffn_gate.input_scale create_tensor: loading tensor blk.0.ffn_down.input_scale create_tensor: loading tensor blk.0.ffn_up.input_scale create_tensor: loading tensor blk.1.attn_q.scale create_tensor: loading tensor blk.1.attn_k.scale create_tensor: loading tensor blk.1.attn_v.scale create_tensor: loading tensor blk.1.attn_output.scale create_tensor: loading tensor blk.1.ffn_gate.scale create_tensor: loading tensor blk.1.ffn_down.scale create_tensor: loading tensor blk.1.ffn_up.scale create_tensor: loading tensor blk.1.attn_q.input_scale create_tensor: loading tensor blk.1.attn_k.input_scale create_tensor: loading tensor blk.1.attn_v.input_scale create_tensor: loading tensor blk.1.attn_output.input_scale create_tensor: loading tensor blk.1.ffn_gate.input_scale create_tensor: loading tensor blk.1.ffn_down.input_scale create_tensor: loading tensor blk.1.ffn_up.input_scale create_tensor: loading tensor blk.2.attn_q.scale create_tensor: loading tensor blk.2.attn_k.scale create_tensor: loading tensor blk.2.attn_v.scale create_tensor: loading tensor blk.2.attn_output.scale create_tensor: loading tensor blk.2.ffn_gate.scale create_tensor: loading tensor blk.2.ffn_down.scale create_tensor: loading tensor blk.2.ffn_up.scale create_tensor: loading tensor blk.2.attn_q.input_scale create_tensor: loading tensor blk.2.attn_k.input_scale create_tensor: loading tensor blk.2.attn_v.input_scale create_tensor: loading tensor blk.2.attn_output.input_scale create_tensor: loading tensor blk.2.ffn_gate.input_scale create_tensor: loading tensor blk.2.ffn_down.input_scale create_tensor: loading tensor blk.2.ffn_up.input_scale create_tensor: loading tensor blk.3.attn_q.scale create_tensor: loading tensor blk.3.attn_k.scale create_tensor: loading tensor blk.3.attn_v.scale create_tensor: loading tensor blk.3.attn_output.scale create_tensor: loading tensor blk.3.ffn_gate.scale create_tensor: loading tensor blk.3.ffn_down.scale create_tensor: loading tensor blk.3.ffn_up.scale create_tensor: loading tensor blk.3.attn_q.input_scale create_tensor: loading tensor blk.3.attn_k.input_scale create_tensor: loading tensor blk.3.attn_v.input_scale create_tensor: loading tensor blk.3.attn_output.input_scale create_tensor: loading tensor blk.3.ffn_gate.input_scale create_tensor: loading tensor blk.3.ffn_down.input_scale create_tensor: loading tensor blk.3.ffn_up.input_scale create_tensor: loading tensor blk.4.attn_q.scale create_tensor: loading tensor blk.4.attn_k.scale create_tensor: loading tensor blk.4.attn_v.scale create_tensor: loading tensor blk.4.attn_output.scale create_tensor: loading tensor blk.4.ffn_gate.scale create_tensor: loading tensor blk.4.ffn_down.scale create_tensor: loading tensor blk.4.ffn_up.scale create_tensor: loading tensor blk.4.attn_q.input_scale create_tensor: loading tensor blk.4.attn_k.input_scale create_tensor: loading tensor blk.4.attn_v.input_scale create_tensor: loading tensor blk.4.attn_output.input_scale create_tensor: loading tensor blk.4.ffn_gate.input_scale create_tensor: loading tensor blk.4.ffn_down.input_scale create_tensor: loading tensor blk.4.ffn_up.input_scale create_tensor: loading tensor blk.5.attn_q.scale create_tensor: loading tensor blk.5.attn_k.scale create_tensor: loading tensor blk.5.attn_v.scale create_tensor: loading tensor blk.5.attn_output.scale create_tensor: loading tensor blk.5.ffn_gate.scale create_tensor: loading tensor blk.5.ffn_down.scale create_tensor: loading tensor blk.5.ffn_up.scale create_tensor: loading tensor blk.5.attn_q.input_scale create_tensor: loading tensor blk.5.attn_k.input_scale create_tensor: loading tensor blk.5.attn_v.input_scale create_tensor: loading tensor blk.5.attn_output.input_scale create_tensor: loading tensor blk.5.ffn_gate.input_scale create_tensor: loading tensor blk.5.ffn_down.input_scale create_tensor: loading tensor blk.5.ffn_up.input_scale create_tensor: loading tensor blk.6.attn_q.scale create_tensor: loading tensor blk.6.attn_k.scale create_tensor: loading tensor blk.6.attn_v.scale create_tensor: loading tensor blk.6.attn_output.scale create_tensor: loading tensor blk.6.ffn_gate.scale create_tensor: loading tensor blk.6.ffn_down.scale create_tensor: loading tensor blk.6.ffn_up.scale create_tensor: loading tensor blk.6.attn_q.input_scale create_tensor: loading tensor blk.6.attn_k.input_scale create_tensor: loading tensor blk.6.attn_v.input_scale create_tensor: loading tensor blk.6.attn_output.input_scale create_tensor: loading tensor blk.6.ffn_gate.input_scale create_tensor: loading tensor blk.6.ffn_down.input_scale create_tensor: loading tensor blk.6.ffn_up.input_scale create_tensor: loading tensor blk.7.attn_q.scale create_tensor: loading tensor blk.7.attn_k.scale create_tensor: loading tensor blk.7.attn_v.scale create_tensor: loading tensor blk.7.attn_output.scale create_tensor: loading tensor blk.7.ffn_gate.scale create_tensor: loading tensor blk.7.ffn_down.scale create_tensor: loading tensor blk.7.ffn_up.scale create_tensor: loading tensor blk.7.attn_q.input_scale create_tensor: loading tensor blk.7.attn_k.input_scale create_tensor: loading tensor blk.7.attn_v.input_scale create_tensor: loading tensor blk.7.attn_output.input_scale create_tensor: loading tensor blk.7.ffn_gate.input_scale create_tensor: loading tensor blk.7.ffn_down.input_scale create_tensor: loading tensor blk.7.ffn_up.input_scale create_tensor: loading tensor blk.8.attn_q.scale create_tensor: loading tensor blk.8.attn_k.scale create_tensor: loading tensor blk.8.attn_v.scale create_tensor: loading tensor blk.8.attn_output.scale create_tensor: loading tensor blk.8.ffn_gate.scale create_tensor: loading tensor blk.8.ffn_down.scale create_tensor: loading tensor blk.8.ffn_up.scale create_tensor: loading tensor blk.8.attn_q.input_scale create_tensor: loading tensor blk.8.attn_k.input_scale create_tensor: loading tensor blk.8.attn_v.input_scale create_tensor: loading tensor blk.8.attn_output.input_scale create_tensor: loading tensor blk.8.ffn_gate.input_scale create_tensor: loading tensor blk.8.ffn_down.input_scale create_tensor: loading tensor blk.8.ffn_up.input_scale create_tensor: loading tensor blk.9.attn_q.scale create_tensor: loading tensor blk.9.attn_k.scale create_tensor: loading tensor blk.9.attn_v.scale create_tensor: loading tensor blk.9.attn_output.scale create_tensor: loading tensor blk.9.ffn_gate.scale create_tensor: loading tensor blk.9.ffn_down.scale create_tensor: loading tensor blk.9.ffn_up.scale create_tensor: loading tensor blk.9.attn_q.input_scale create_tensor: loading tensor blk.9.attn_k.input_scale create_tensor: loading tensor blk.9.attn_v.input_scale create_tensor: loading tensor blk.9.attn_output.input_scale create_tensor: loading tensor blk.9.ffn_gate.input_scale create_tensor: loading tensor blk.9.ffn_down.input_scale create_tensor: loading tensor blk.9.ffn_up.input_scale create_tensor: loading tensor blk.10.attn_q.scale create_tensor: loading tensor blk.10.attn_k.scale create_tensor: loading tensor blk.10.attn_v.scale create_tensor: loading tensor blk.10.attn_output.scale create_tensor: loading tensor blk.10.ffn_gate.scale create_tensor: loading tensor blk.10.ffn_down.scale create_tensor: loading tensor blk.10.ffn_up.scale create_tensor: loading tensor blk.10.attn_q.input_scale create_tensor: loading tensor blk.10.attn_k.input_scale create_tensor: loading tensor blk.10.attn_v.input_scale create_tensor: loading tensor blk.10.attn_output.input_scale create_tensor: loading tensor blk.10.ffn_gate.input_scale create_tensor: loading tensor blk.10.ffn_down.input_scale create_tensor: loading tensor blk.10.ffn_up.input_scale create_tensor: loading tensor blk.11.attn_q.scale create_tensor: loading tensor blk.11.attn_k.scale create_tensor: loading tensor blk.11.attn_v.scale create_tensor: loading tensor blk.11.attn_output.scale create_tensor: loading tensor blk.11.ffn_gate.scale create_tensor: loading tensor blk.11.ffn_down.scale create_tensor: loading tensor blk.11.ffn_up.scale create_tensor: loading tensor blk.11.attn_q.input_scale create_tensor: loading tensor blk.11.attn_k.input_scale create_tensor: loading tensor blk.11.attn_v.input_scale create_tensor: loading tensor blk.11.attn_output.input_scale create_tensor: loading tensor blk.11.ffn_gate.input_scale create_tensor: loading tensor blk.11.ffn_down.input_scale create_tensor: loading tensor blk.11.ffn_up.input_scale create_tensor: loading tensor blk.12.attn_q.scale create_tensor: loading tensor blk.12.attn_k.scale create_tensor: loading tensor blk.12.attn_v.scale create_tensor: loading tensor blk.12.attn_output.scale create_tensor: loading tensor blk.12.ffn_gate.scale create_tensor: loading tensor blk.12.ffn_down.scale create_tensor: loading tensor blk.12.ffn_up.scale create_tensor: loading tensor blk.12.attn_q.input_scale create_tensor: loading tensor blk.12.attn_k.input_scale create_tensor: loading tensor blk.12.attn_v.input_scale create_tensor: loading tensor blk.12.attn_output.input_scale create_tensor: loading tensor blk.12.ffn_gate.input_scale create_tensor: loading tensor blk.12.ffn_down.input_scale create_tensor: loading tensor blk.12.ffn_up.input_scale create_tensor: loading tensor blk.13.attn_q.scale create_tensor: loading tensor blk.13.attn_k.scale create_tensor: loading tensor blk.13.attn_v.scale create_tensor: loading tensor blk.13.attn_output.scale create_tensor: loading tensor blk.13.ffn_gate.scale create_tensor: loading tensor blk.13.ffn_down.scale create_tensor: loading tensor blk.13.ffn_up.scale create_tensor: loading tensor blk.13.attn_q.input_scale create_tensor: loading tensor blk.13.attn_k.input_scale create_tensor: loading tensor blk.13.attn_v.input_scale create_tensor: loading tensor blk.13.attn_output.input_scale create_tensor: loading tensor blk.13.ffn_gate.input_scale create_tensor: loading tensor blk.13.ffn_down.input_scale create_tensor: loading tensor blk.13.ffn_up.input_scale create_tensor: loading tensor blk.14.attn_q.scale create_tensor: loading tensor blk.14.attn_k.scale create_tensor: loading tensor blk.14.attn_v.scale create_tensor: loading tensor blk.14.attn_output.scale create_tensor: loading tensor blk.14.ffn_gate.scale create_tensor: loading tensor blk.14.ffn_down.scale create_tensor: loading tensor blk.14.ffn_up.scale create_tensor: loading tensor blk.14.attn_q.input_scale create_tensor: loading tensor blk.14.attn_k.input_scale create_tensor: loading tensor blk.14.attn_v.input_scale create_tensor: loading tensor blk.14.attn_output.input_scale create_tensor: loading tensor blk.14.ffn_gate.input_scale create_tensor: loading tensor blk.14.ffn_down.input_scale create_tensor: loading tensor blk.14.ffn_up.input_scale create_tensor: loading tensor blk.15.attn_q.scale create_tensor: loading tensor blk.15.attn_k.scale create_tensor: loading tensor blk.15.attn_v.scale create_tensor: loading tensor blk.15.attn_output.scale create_tensor: loading tensor blk.15.ffn_gate.scale create_tensor: loading tensor blk.15.ffn_down.scale create_tensor: loading tensor blk.15.ffn_up.scale create_tensor: loading tensor blk.15.attn_q.input_scale create_tensor: loading tensor blk.15.attn_k.input_scale create_tensor: loading tensor blk.15.attn_v.input_scale create_tensor: loading tensor blk.15.attn_output.input_scale create_tensor: loading tensor blk.15.ffn_gate.input_scale create_tensor: loading tensor blk.15.ffn_down.input_scale create_tensor: loading tensor blk.15.ffn_up.input_scale create_tensor: loading tensor blk.16.attn_q.scale create_tensor: loading tensor blk.16.attn_k.scale create_tensor: loading tensor blk.16.attn_v.scale create_tensor: loading tensor blk.16.attn_output.scale create_tensor: loading tensor blk.16.ffn_gate.scale create_tensor: loading tensor blk.16.ffn_down.scale create_tensor: loading tensor blk.16.ffn_up.scale create_tensor: loading tensor blk.16.attn_q.input_scale create_tensor: loading tensor blk.16.attn_k.input_scale create_tensor: loading tensor blk.16.attn_v.input_scale create_tensor: loading tensor blk.16.attn_output.input_scale create_tensor: loading tensor blk.16.ffn_gate.input_scale create_tensor: loading tensor blk.16.ffn_down.input_scale create_tensor: loading tensor blk.16.ffn_up.input_scale create_tensor: loading tensor blk.17.attn_q.scale create_tensor: loading tensor blk.17.attn_k.scale create_tensor: loading tensor blk.17.attn_v.scale create_tensor: loading tensor blk.17.attn_output.scale create_tensor: loading tensor blk.17.ffn_gate.scale create_tensor: loading tensor blk.17.ffn_down.scale create_tensor: loading tensor blk.17.ffn_up.scale create_tensor: loading tensor blk.17.attn_q.input_scale create_tensor: loading tensor blk.17.attn_k.input_scale create_tensor: loading tensor blk.17.attn_v.input_scale create_tensor: loading tensor blk.17.attn_output.input_scale create_tensor: loading tensor blk.17.ffn_gate.input_scale create_tensor: loading tensor blk.17.ffn_down.input_scale create_tensor: loading tensor blk.17.ffn_up.input_scale create_tensor: loading tensor blk.18.attn_q.scale create_tensor: loading tensor blk.18.attn_k.scale create_tensor: loading tensor blk.18.attn_v.scale create_tensor: loading tensor blk.18.attn_output.scale create_tensor: loading tensor blk.18.ffn_gate.scale create_tensor: loading tensor blk.18.ffn_down.scale create_tensor: loading tensor blk.18.ffn_up.scale create_tensor: loading tensor blk.18.attn_q.input_scale create_tensor: loading tensor blk.18.attn_k.input_scale create_tensor: loading tensor blk.18.attn_v.input_scale create_tensor: loading tensor blk.18.attn_output.input_scale create_tensor: loading tensor blk.18.ffn_gate.input_scale create_tensor: loading tensor blk.18.ffn_down.input_scale create_tensor: loading tensor blk.18.ffn_up.input_scale create_tensor: loading tensor blk.19.attn_q.scale create_tensor: loading tensor blk.19.attn_k.scale create_tensor: loading tensor blk.19.attn_v.scale create_tensor: loading tensor blk.19.attn_output.scale create_tensor: loading tensor blk.19.ffn_gate.scale create_tensor: loading tensor blk.19.ffn_down.scale create_tensor: loading tensor blk.19.ffn_up.scale create_tensor: loading tensor blk.19.attn_q.input_scale create_tensor: loading tensor blk.19.attn_k.input_scale create_tensor: loading tensor blk.19.attn_v.input_scale create_tensor: loading tensor blk.19.attn_output.input_scale create_tensor: loading tensor blk.19.ffn_gate.input_scale create_tensor: loading tensor blk.19.ffn_down.input_scale create_tensor: loading tensor blk.19.ffn_up.input_scale create_tensor: loading tensor blk.20.attn_q.scale create_tensor: loading tensor blk.20.attn_k.scale create_tensor: loading tensor blk.20.attn_v.scale create_tensor: loading tensor blk.20.attn_output.scale create_tensor: loading tensor blk.20.ffn_gate.scale create_tensor: loading tensor blk.20.ffn_down.scale create_tensor: loading tensor blk.20.ffn_up.scale create_tensor: loading tensor blk.20.attn_q.input_scale create_tensor: loading tensor blk.20.attn_k.input_scale create_tensor: loading tensor blk.20.attn_v.input_scale create_tensor: loading tensor blk.20.attn_output.input_scale create_tensor: loading tensor blk.20.ffn_gate.input_scale create_tensor: loading tensor blk.20.ffn_down.input_scale create_tensor: loading tensor blk.20.ffn_up.input_scale create_tensor: loading tensor blk.21.attn_q.scale create_tensor: loading tensor blk.21.attn_k.scale create_tensor: loading tensor blk.21.attn_v.scale create_tensor: loading tensor blk.21.attn_output.scale create_tensor: loading tensor blk.21.ffn_gate.scale create_tensor: loading tensor blk.21.ffn_down.scale create_tensor: loading tensor blk.21.ffn_up.scale create_tensor: loading tensor blk.21.attn_q.input_scale create_tensor: loading tensor blk.21.attn_k.input_scale create_tensor: loading tensor blk.21.attn_v.input_scale create_tensor: loading tensor blk.21.attn_output.input_scale create_tensor: loading tensor blk.21.ffn_gate.input_scale create_tensor: loading tensor blk.21.ffn_down.input_scale create_tensor: loading tensor blk.21.ffn_up.input_scale create_tensor: loading tensor blk.22.attn_q.scale create_tensor: loading tensor blk.22.attn_k.scale create_tensor: loading tensor blk.22.attn_v.scale create_tensor: loading tensor blk.22.attn_output.scale create_tensor: loading tensor blk.22.ffn_gate.scale create_tensor: loading tensor blk.22.ffn_down.scale create_tensor: loading tensor blk.22.ffn_up.scale create_tensor: loading tensor blk.22.attn_q.input_scale create_tensor: loading tensor blk.22.attn_k.input_scale create_tensor: loading tensor blk.22.attn_v.input_scale create_tensor: loading tensor blk.22.attn_output.input_scale create_tensor: loading tensor blk.22.ffn_gate.input_scale create_tensor: loading tensor blk.22.ffn_down.input_scale create_tensor: loading tensor blk.22.ffn_up.input_scale create_tensor: loading tensor blk.23.attn_q.scale create_tensor: loading tensor blk.23.attn_k.scale create_tensor: loading tensor blk.23.attn_v.scale create_tensor: loading tensor blk.23.attn_output.scale create_tensor: loading tensor blk.23.ffn_gate.scale create_tensor: loading tensor blk.23.ffn_down.scale create_tensor: loading tensor blk.23.ffn_up.scale create_tensor: loading tensor blk.23.attn_q.input_scale create_tensor: loading tensor blk.23.attn_k.input_scale create_tensor: loading tensor blk.23.attn_v.input_scale create_tensor: loading tensor blk.23.attn_output.input_scale create_tensor: loading tensor blk.23.ffn_gate.input_scale create_tensor: loading tensor blk.23.ffn_down.input_scale create_tensor: loading tensor blk.23.ffn_up.input_scale create_tensor: loading tensor blk.24.attn_q.scale create_tensor: loading tensor blk.24.attn_k.scale create_tensor: loading tensor blk.24.attn_v.scale create_tensor: loading tensor blk.24.attn_output.scale create_tensor: loading tensor blk.24.ffn_gate.scale create_tensor: loading tensor blk.24.ffn_down.scale create_tensor: loading tensor blk.24.ffn_up.scale create_tensor: loading tensor blk.24.attn_q.input_scale create_tensor: loading tensor blk.24.attn_k.input_scale create_tensor: loading tensor blk.24.attn_v.input_scale create_tensor: loading tensor blk.24.attn_output.input_scale create_tensor: loading tensor blk.24.ffn_gate.input_scale create_tensor: loading tensor blk.24.ffn_down.input_scale create_tensor: loading tensor blk.24.ffn_up.input_scale create_tensor: loading tensor blk.25.attn_q.scale create_tensor: loading tensor blk.25.attn_k.scale create_tensor: loading tensor blk.25.attn_v.scale create_tensor: loading tensor blk.25.attn_output.scale create_tensor: loading tensor blk.25.ffn_gate.scale create_tensor: loading tensor blk.25.ffn_down.scale create_tensor: loading tensor blk.25.ffn_up.scale create_tensor: loading tensor blk.25.attn_q.input_scale create_tensor: loading tensor blk.25.attn_k.input_scale create_tensor: loading tensor blk.25.attn_v.input_scale create_tensor: loading tensor blk.25.attn_output.input_scale create_tensor: loading tensor blk.25.ffn_gate.input_scale create_tensor: loading tensor blk.25.ffn_down.input_scale create_tensor: loading tensor blk.25.ffn_up.input_scale create_tensor: loading tensor blk.26.attn_q.scale create_tensor: loading tensor blk.26.attn_k.scale create_tensor: loading tensor blk.26.attn_v.scale create_tensor: loading tensor blk.26.attn_output.scale create_tensor: loading tensor blk.26.ffn_gate.scale create_tensor: loading tensor blk.26.ffn_down.scale create_tensor: loading tensor blk.26.ffn_up.scale create_tensor: loading tensor blk.26.attn_q.input_scale create_tensor: loading tensor blk.26.attn_k.input_scale create_tensor: loading tensor blk.26.attn_v.input_scale create_tensor: loading tensor blk.26.attn_output.input_scale create_tensor: loading tensor blk.26.ffn_gate.input_scale create_tensor: loading tensor blk.26.ffn_down.input_scale create_tensor: loading tensor blk.26.ffn_up.input_scale create_tensor: loading tensor blk.27.attn_q.scale create_tensor: loading tensor blk.27.attn_k.scale create_tensor: loading tensor blk.27.attn_v.scale create_tensor: loading tensor blk.27.attn_output.scale create_tensor: loading tensor blk.27.ffn_gate.scale create_tensor: loading tensor blk.27.ffn_down.scale create_tensor: loading tensor blk.27.ffn_up.scale create_tensor: loading tensor blk.27.attn_q.input_scale create_tensor: loading tensor blk.27.attn_k.input_scale create_tensor: loading tensor blk.27.attn_v.input_scale create_tensor: loading tensor blk.27.attn_output.input_scale create_tensor: loading tensor blk.27.ffn_gate.input_scale create_tensor: loading tensor blk.27.ffn_down.input_scale create_tensor: loading tensor blk.27.ffn_up.input_scale create_tensor: loading tensor blk.28.attn_q.scale create_tensor: loading tensor blk.28.attn_k.scale create_tensor: loading tensor blk.28.attn_v.scale create_tensor: loading tensor blk.28.attn_output.scale create_tensor: loading tensor blk.28.ffn_gate.scale create_tensor: loading tensor blk.28.ffn_down.scale create_tensor: loading tensor blk.28.ffn_up.scale create_tensor: loading tensor blk.28.attn_q.input_scale create_tensor: loading tensor blk.28.attn_k.input_scale create_tensor: loading tensor blk.28.attn_v.input_scale create_tensor: loading tensor blk.28.attn_output.input_scale create_tensor: loading tensor blk.28.ffn_gate.input_scale create_tensor: loading tensor blk.28.ffn_down.input_scale create_tensor: loading tensor blk.28.ffn_up.input_scale create_tensor: loading tensor blk.29.attn_q.scale create_tensor: loading tensor blk.29.attn_k.scale create_tensor: loading tensor blk.29.attn_v.scale create_tensor: loading tensor blk.29.attn_output.scale create_tensor: loading tensor blk.29.ffn_gate.scale create_tensor: loading tensor blk.29.ffn_down.scale create_tensor: loading tensor blk.29.ffn_up.scale create_tensor: loading tensor blk.29.attn_q.input_scale create_tensor: loading tensor blk.29.attn_k.input_scale create_tensor: loading tensor blk.29.attn_v.input_scale create_tensor: loading tensor blk.29.attn_output.input_scale create_tensor: loading tensor blk.29.ffn_gate.input_scale create_tensor: loading tensor blk.29.ffn_down.input_scale create_tensor: loading tensor blk.29.ffn_up.input_scale create_tensor: loading tensor blk.30.attn_q.scale create_tensor: loading tensor blk.30.attn_k.scale create_tensor: loading tensor blk.30.attn_v.scale create_tensor: loading tensor blk.30.attn_output.scale create_tensor: loading tensor blk.30.ffn_gate.scale create_tensor: loading tensor blk.30.ffn_down.scale create_tensor: loading tensor blk.30.ffn_up.scale create_tensor: loading tensor blk.30.attn_q.input_scale create_tensor: loading tensor blk.30.attn_k.input_scale create_tensor: loading tensor blk.30.attn_v.input_scale create_tensor: loading tensor blk.30.attn_output.input_scale create_tensor: loading tensor blk.30.ffn_gate.input_scale create_tensor: loading tensor blk.30.ffn_down.input_scale create_tensor: loading tensor blk.30.ffn_up.input_scale create_tensor: loading tensor blk.31.attn_q.scale create_tensor: loading tensor blk.31.attn_k.scale create_tensor: loading tensor blk.31.attn_v.scale create_tensor: loading tensor blk.31.attn_output.scale create_tensor: loading tensor blk.31.ffn_gate.scale create_tensor: loading tensor blk.31.ffn_down.scale create_tensor: loading tensor blk.31.ffn_up.scale create_tensor: loading tensor blk.31.attn_q.input_scale create_tensor: loading tensor blk.31.attn_k.input_scale create_tensor: loading tensor blk.31.attn_v.input_scale create_tensor: loading tensor blk.31.attn_output.input_scale create_tensor: loading tensor blk.31.ffn_gate.input_scale create_tensor: loading tensor blk.31.ffn_down.input_scale create_tensor: loading tensor blk.31.ffn_up.input_scale create_tensor: loading tensor blk.32.attn_q.scale create_tensor: loading tensor blk.32.attn_k.scale create_tensor: loading tensor blk.32.attn_v.scale create_tensor: loading tensor blk.32.attn_output.scale create_tensor: loading tensor blk.32.ffn_gate.scale create_tensor: loading tensor blk.32.ffn_down.scale create_tensor: loading tensor blk.32.ffn_up.scale create_tensor: loading tensor blk.32.attn_q.input_scale create_tensor: loading tensor blk.32.attn_k.input_scale create_tensor: loading tensor blk.32.attn_v.input_scale create_tensor: loading tensor blk.32.attn_output.input_scale create_tensor: loading tensor blk.32.ffn_gate.input_scale create_tensor: loading tensor blk.32.ffn_down.input_scale create_tensor: loading tensor blk.32.ffn_up.input_scale create_tensor: loading tensor blk.33.attn_q.scale create_tensor: loading tensor blk.33.attn_k.scale create_tensor: loading tensor blk.33.attn_v.scale create_tensor: loading tensor blk.33.attn_output.scale create_tensor: loading tensor blk.33.ffn_gate.scale create_tensor: loading tensor blk.33.ffn_down.scale create_tensor: loading tensor blk.33.ffn_up.scale create_tensor: loading tensor blk.33.attn_q.input_scale create_tensor: loading tensor blk.33.attn_k.input_scale create_tensor: loading tensor blk.33.attn_v.input_scale create_tensor: loading tensor blk.33.attn_output.input_scale create_tensor: loading tensor blk.33.ffn_gate.input_scale create_tensor: loading tensor blk.33.ffn_down.input_scale create_tensor: loading tensor blk.33.ffn_up.input_scale create_tensor: loading tensor blk.34.attn_q.scale create_tensor: loading tensor blk.34.attn_k.scale create_tensor: loading tensor blk.34.attn_v.scale create_tensor: loading tensor blk.34.attn_output.scale create_tensor: loading tensor blk.34.ffn_gate.scale create_tensor: loading tensor blk.34.ffn_down.scale create_tensor: loading tensor blk.34.ffn_up.scale create_tensor: loading tensor blk.34.attn_q.input_scale create_tensor: loading tensor blk.34.attn_k.input_scale create_tensor: loading tensor blk.34.attn_v.input_scale create_tensor: loading tensor blk.34.attn_output.input_scale create_tensor: loading tensor blk.34.ffn_gate.input_scale create_tensor: loading tensor blk.34.ffn_down.input_scale create_tensor: loading tensor blk.34.ffn_up.input_scale create_tensor: loading tensor blk.35.attn_q.scale create_tensor: loading tensor blk.35.attn_k.scale create_tensor: loading tensor blk.35.attn_v.scale create_tensor: loading tensor blk.35.attn_output.scale create_tensor: loading tensor blk.35.ffn_gate.scale create_tensor: loading tensor blk.35.ffn_down.scale create_tensor: loading tensor blk.35.ffn_up.scale create_tensor: loading tensor blk.35.attn_q.input_scale create_tensor: loading tensor blk.35.attn_k.input_scale create_tensor: loading tensor blk.35.attn_v.input_scale create_tensor: loading tensor blk.35.attn_output.input_scale create_tensor: loading tensor blk.35.ffn_gate.input_scale create_tensor: loading tensor blk.35.ffn_down.input_scale create_tensor: loading tensor blk.35.ffn_up.input_scale create_tensor: loading tensor blk.36.attn_q.scale create_tensor: loading tensor blk.36.attn_k.scale create_tensor: loading tensor blk.36.attn_v.scale create_tensor: loading tensor blk.36.attn_output.scale create_tensor: loading tensor blk.36.ffn_gate.scale create_tensor: loading tensor blk.36.ffn_down.scale create_tensor: loading tensor blk.36.ffn_up.scale create_tensor: loading tensor blk.36.attn_q.input_scale create_tensor: loading tensor blk.36.attn_k.input_scale create_tensor: loading tensor blk.36.attn_v.input_scale create_tensor: loading tensor blk.36.attn_output.input_scale create_tensor: loading tensor blk.36.ffn_gate.input_scale create_tensor: loading tensor blk.36.ffn_down.input_scale create_tensor: loading tensor blk.36.ffn_up.input_scale create_tensor: loading tensor blk.37.attn_q.scale create_tensor: loading tensor blk.37.attn_k.scale create_tensor: loading tensor blk.37.attn_v.scale create_tensor: loading tensor blk.37.attn_output.scale create_tensor: loading tensor blk.37.ffn_gate.scale create_tensor: loading tensor blk.37.ffn_down.scale create_tensor: loading tensor blk.37.ffn_up.scale create_tensor: loading tensor blk.37.attn_q.input_scale create_tensor: loading tensor blk.37.attn_k.input_scale create_tensor: loading tensor blk.37.attn_v.input_scale create_tensor: loading tensor blk.37.attn_output.input_scale create_tensor: loading tensor blk.37.ffn_gate.input_scale create_tensor: loading tensor blk.37.ffn_down.input_scale create_tensor: loading tensor blk.37.ffn_up.input_scale create_tensor: loading tensor blk.38.attn_q.scale create_tensor: loading tensor blk.38.attn_k.scale create_tensor: loading tensor blk.38.attn_v.scale create_tensor: loading tensor blk.38.attn_output.scale create_tensor: loading tensor blk.38.ffn_gate.scale create_tensor: loading tensor blk.38.ffn_down.scale create_tensor: loading tensor blk.38.ffn_up.scale create_tensor: loading tensor blk.38.attn_q.input_scale create_tensor: loading tensor blk.38.attn_k.input_scale create_tensor: loading tensor blk.38.attn_v.input_scale create_tensor: loading tensor blk.38.attn_output.input_scale create_tensor: loading tensor blk.38.ffn_gate.input_scale create_tensor: loading tensor blk.38.ffn_down.input_scale create_tensor: loading tensor blk.38.ffn_up.input_scale create_tensor: loading tensor blk.39.attn_q.scale create_tensor: loading tensor blk.39.attn_k.scale create_tensor: loading tensor blk.39.attn_v.scale create_tensor: loading tensor blk.39.attn_output.scale create_tensor: loading tensor blk.39.ffn_gate.scale create_tensor: loading tensor blk.39.ffn_down.scale create_tensor: loading tensor blk.39.ffn_up.scale create_tensor: loading tensor blk.39.attn_q.input_scale create_tensor: loading tensor blk.39.attn_k.input_scale create_tensor: loading tensor blk.39.attn_v.input_scale create_tensor: loading tensor blk.39.attn_output.input_scale create_tensor: loading tensor blk.39.ffn_gate.input_scale create_tensor: loading tensor blk.39.ffn_down.input_scale create_tensor: loading tensor blk.39.ffn_up.input_scale done_getting_tensors: tensor 'token_embd.weight' (q4_K) (and 0 others) cannot be used with preferred buffer type Vulkan_Host, using CPU instead load_tensors: offloading output layer to GPU load_tensors: offloading 39 repeating layers to GPU load_tensors: offloaded 41/41 layers to GPU load_tensors: CPU_Mapped model buffer size = 417.30 MiB load_tensors: Vulkan1 model buffer size = 8423.47 MiB ........................................................................................... llama_context: constructing llama_context llama_context: n_seq_max = 1 llama_context: n_ctx = 8704 llama_context: n_ctx_seq = 8704 llama_context: n_batch = 2048 llama_context: n_ubatch = 512 llama_context: causal_attn = 1 llama_context: flash_attn = auto llama_context: kv_unified = false llama_context: freq_base = 1000000.0 llama_context: freq_scale = 1 llama_context: n_rs_seq = 0 llama_context: n_outputs_max = 2048 llama_context: n_outputs_max_per_seq = 1 llama_context: n_ctx_seq (8704) < n_ctx_train (40960) -- the full capacity of the model will not be utilized set_abort_callback: call llama_context: Vulkan_Host output buffer size = 0.58 MiB llama_kv_cache: layer 0: dev = Vulkan1 llama_kv_cache: layer 1: dev = Vulkan1 llama_kv_cache: layer 2: dev = Vulkan1 llama_kv_cache: layer 3: dev = Vulkan1 llama_kv_cache: layer 4: dev = Vulkan1 llama_kv_cache: layer 5: dev = Vulkan1 llama_kv_cache: layer 6: dev = Vulkan1 llama_kv_cache: layer 7: dev = Vulkan1 llama_kv_cache: layer 8: dev = Vulkan1 llama_kv_cache: layer 9: dev = Vulkan1 llama_kv_cache: layer 10: dev = Vulkan1 llama_kv_cache: layer 11: dev = Vulkan1 llama_kv_cache: layer 12: dev = Vulkan1 llama_kv_cache: layer 13: dev = Vulkan1 llama_kv_cache: layer 14: dev = Vulkan1 llama_kv_cache: layer 15: dev = Vulkan1 llama_kv_cache: layer 16: dev = Vulkan1 llama_kv_cache: layer 17: dev = Vulkan1 llama_kv_cache: layer 18: dev = Vulkan1 llama_kv_cache: layer 19: dev = Vulkan1 llama_kv_cache: layer 20: dev = Vulkan1 llama_kv_cache: layer 21: dev = Vulkan1 llama_kv_cache: layer 22: dev = Vulkan1 llama_kv_cache: layer 23: dev = Vulkan1 llama_kv_cache: layer 24: dev = Vulkan1 llama_kv_cache: layer 25: dev = Vulkan1 llama_kv_cache: layer 26: dev = Vulkan1 llama_kv_cache: layer 27: dev = Vulkan1 llama_kv_cache: layer 28: dev = Vulkan1 llama_kv_cache: layer 29: dev = Vulkan1 llama_kv_cache: layer 30: dev = Vulkan1 llama_kv_cache: layer 31: dev = Vulkan1 llama_kv_cache: layer 32: dev = Vulkan1 llama_kv_cache: layer 33: dev = Vulkan1 llama_kv_cache: layer 34: dev = Vulkan1 llama_kv_cache: layer 35: dev = Vulkan1 llama_kv_cache: layer 36: dev = Vulkan1 llama_kv_cache: layer 37: dev = Vulkan1 llama_kv_cache: layer 38: dev = Vulkan1 llama_kv_cache: layer 39: dev = Vulkan1 llama_kv_cache: Vulkan1 KV buffer size = 1360.00 MiB llama_kv_cache: size = 1360.00 MiB ( 8704 cells, 40 layers, 1/1 seqs), K (f16): 680.00 MiB, V (f16): 680.00 MiB llama_kv_cache: attn_rot_k = 0, n_embd_head_k_all = 128 llama_kv_cache: attn_rot_v = 0, n_embd_head_k_all = 128 llama_context: enumerating backends llama_context: backend_ptrs.size() = 2 sched_reserve: reserving ... sched_reserve: max_nodes = 3544 sched_reserve: reserving full memory module sched_reserve: worst-case: n_tokens = 512, n_seqs = 1, n_outputs = 1 graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 1, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) resolve_fused_ops: Flash Attention enabled resolve_fused_ops: resolving fused DeepSeek V4 HC support: graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 1, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) resolve_fused_ops: fused DeepSeek V4 HC pre enabled graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 1, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) resolve_fused_ops: fused DeepSeek V4 HC comb enabled graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 1, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) resolve_fused_ops: fused DeepSeek V4 HC post enabled graph_reserve: reserving a graph for ubatch with n_tokens = 512, n_seqs = 1, n_outputs = 512 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 512, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 512, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 512, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 1, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 1, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) graph_reserve: reserving a graph for ubatch with n_tokens = 512, n_seqs = 1, n_outputs = 512 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 512, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8704, 512, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 512, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 512, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) sched_reserve: Vulkan1 compute buffer size = 316.75 MiB sched_reserve: Vulkan_Host compute buffer size = 28.51 MiB sched_reserve: graph: nodes = 1406, splits = 2, input objects = 4, input tensors = 6 sched_reserve: reserve took 49.46 ms, sched copies = 1 attach_threadpool: call set_n_threads: n_threads = 8, n_threads_batch = 8 set_n_threads: n_threads = 8, n_threads_batch = 8 set_n_threads: n_threads = 8, n_threads_batch = 8 state_read_meta: cell_count = 8192, dest_seq_id = 0 set_n_threads: n_threads = 8, n_threads_batch = 8 state_read_meta: cell_count = 8192, dest_seq_id = 0 set_n_threads: n_threads = 8, n_threads_batch = 8 state_read_meta: cell_count = 8192, dest_seq_id = 0 set_n_threads: n_threads = 8, n_threads_batch = 8 state_read_meta: cell_count = 8192, dest_seq_id = 0 set_n_threads: n_threads = 8, n_threads_batch = 8 llama_perf_context_print: load time = 5813.43 ms llama_perf_context_print: prompt eval time = 0.00 ms / 11264 tokens ( 0.00 ms per token, inf tokens per second) llama_perf_context_print: eval time = 0.00 ms / 1 runs ( 0.00 ms per token, inf tokens per second) llama_perf_context_print: total time = 14673.87 ms / 11265 tokens llama_perf_context_print: graphs reused = 4 ~llama_context: Vulkan1 compute buffer size is 316.7500 MiB, matches expectation of 316.7500 MiB ~llama_context: Vulkan_Host compute buffer size is 28.5137 MiB, matches expectation of 28.5137 MiB llama_context: constructing llama_context llama_context: n_seq_max = 1 llama_context: n_ctx = 8448 llama_context: n_ctx_seq = 8448 llama_context: n_batch = 2048 llama_context: n_ubatch = 512 llama_context: causal_attn = 1 llama_context: flash_attn = auto llama_context: kv_unified = false llama_context: freq_base = 1000000.0 llama_context: freq_scale = 1 llama_context: n_rs_seq = 0 llama_context: n_outputs_max = 2048 llama_context: n_outputs_max_per_seq = 1 llama_context: n_ctx_seq (8448) < n_ctx_train (40960) -- the full capacity of the model will not be utilized set_abort_callback: call llama_context: Vulkan_Host output buffer size = 0.58 MiB llama_kv_cache: layer 0: dev = Vulkan1 llama_kv_cache: layer 1: dev = Vulkan1 llama_kv_cache: layer 2: dev = Vulkan1 llama_kv_cache: layer 3: dev = Vulkan1 llama_kv_cache: layer 4: dev = Vulkan1 llama_kv_cache: layer 5: dev = Vulkan1 llama_kv_cache: layer 6: dev = Vulkan1 llama_kv_cache: layer 7: dev = Vulkan1 llama_kv_cache: layer 8: dev = Vulkan1 llama_kv_cache: layer 9: dev = Vulkan1 llama_kv_cache: layer 10: dev = Vulkan1 llama_kv_cache: layer 11: dev = Vulkan1 llama_kv_cache: layer 12: dev = Vulkan1 llama_kv_cache: layer 13: dev = Vulkan1 llama_kv_cache: layer 14: dev = Vulkan1 llama_kv_cache: layer 15: dev = Vulkan1 llama_kv_cache: layer 16: dev = Vulkan1 llama_kv_cache: layer 17: dev = Vulkan1 llama_kv_cache: layer 18: dev = Vulkan1 llama_kv_cache: layer 19: dev = Vulkan1 llama_kv_cache: layer 20: dev = Vulkan1 llama_kv_cache: layer 21: dev = Vulkan1 llama_kv_cache: layer 22: dev = Vulkan1 llama_kv_cache: layer 23: dev = Vulkan1 llama_kv_cache: layer 24: dev = Vulkan1 llama_kv_cache: layer 25: dev = Vulkan1 llama_kv_cache: layer 26: dev = Vulkan1 llama_kv_cache: layer 27: dev = Vulkan1 llama_kv_cache: layer 28: dev = Vulkan1 llama_kv_cache: layer 29: dev = Vulkan1 llama_kv_cache: layer 30: dev = Vulkan1 llama_kv_cache: layer 31: dev = Vulkan1 llama_kv_cache: layer 32: dev = Vulkan1 llama_kv_cache: layer 33: dev = Vulkan1 llama_kv_cache: layer 34: dev = Vulkan1 llama_kv_cache: layer 35: dev = Vulkan1 llama_kv_cache: layer 36: dev = Vulkan1 llama_kv_cache: layer 37: dev = Vulkan1 llama_kv_cache: layer 38: dev = Vulkan1 llama_kv_cache: layer 39: dev = Vulkan1 llama_kv_cache: Vulkan1 KV buffer size = 1320.00 MiB llama_kv_cache: size = 1320.00 MiB ( 8448 cells, 40 layers, 1/1 seqs), K (f16): 660.00 MiB, V (f16): 660.00 MiB llama_kv_cache: attn_rot_k = 0, n_embd_head_k_all = 128 llama_kv_cache: attn_rot_v = 0, n_embd_head_k_all = 128 llama_context: enumerating backends llama_context: backend_ptrs.size() = 2 sched_reserve: reserving ... sched_reserve: max_nodes = 3544 sched_reserve: reserving full memory module sched_reserve: worst-case: n_tokens = 512, n_seqs = 1, n_outputs = 1 graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 1, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) resolve_fused_ops: Flash Attention enabled resolve_fused_ops: resolving fused DeepSeek V4 HC support: graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 1, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) resolve_fused_ops: fused DeepSeek V4 HC pre enabled graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 1, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) resolve_fused_ops: fused DeepSeek V4 HC comb enabled graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 1, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) resolve_fused_ops: fused DeepSeek V4 HC post enabled graph_reserve: reserving a graph for ubatch with n_tokens = 512, n_seqs = 1, n_outputs = 512 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 512, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 512, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 512, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) graph_reserve: reserving a graph for ubatch with n_tokens = 1, n_seqs = 1, n_outputs = 1 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 1, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 1, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 1, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 1, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 1, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) graph_reserve: reserving a graph for ubatch with n_tokens = 512, n_seqs = 1, n_outputs = 512 llama_graph_n_input_tensors: input tensor ' inp_tokens' [i32, ne = { 512, 1, 1, 1 }] is used by node 'embd' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-0' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-1' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-2' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-3' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-4' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-5' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-6' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-7' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-8' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-9' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-10' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-11' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-12' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-13' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-14' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-15' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-16' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-17' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-18' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-19' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-20' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-21' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-22' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-23' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-24' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-25' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-26' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-27' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-28' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-29' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-30' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-31' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-32' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-33' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-34' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-35' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-36' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-37' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-38' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Qcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' inp_pos' [i32, ne = { 512, 1, 1, 1 }] is used by node 'Kcur-39' (ROPE) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_k_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_k_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l0 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l1 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l2 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l3 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l4 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l5 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l6 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l7 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l8 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l9 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l10 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l11 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l12 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l13 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l14 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l15 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l16 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l17 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l18 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l19 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l20 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l21 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l22 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l23 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l24 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l25 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l26 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l27 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l28 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l29 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l30 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l31 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l32 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l33 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l34 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l35 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l36 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l37 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l38 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_v_idxs' [i64, ne = { 512, 1, 1, 1 }] is used by node 'cache_v_l39 (view)' (SET_ROWS) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_25' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_60' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_95' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_130' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_165' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_200' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_235' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_270' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_305' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_340' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_375' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_410' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_445' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_480' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_515' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_550' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_585' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_620' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_655' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_690' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_725' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_760' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_795' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_830' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_865' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_900' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_935' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_970' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1005' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1040' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1075' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1110' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1145' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1180' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1215' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1250' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1285' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1320' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1355' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' attn_inp_kq_mask' [f16, ne = { 8448, 512, 1, 1 }] is used by node 'node_1390' (FLASH_ATTN_EXT) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 512, 1, 1, 1 }] is used by node 'node_1393' (GET_ROWS) llama_graph_n_input_tensors: input tensor ' out_ids' [i32, ne = { 512, 1, 1, 1 }] is used by node 'node_1394' (GET_ROWS) sched_reserve: Vulkan1 compute buffer size = 316.75 MiB sched_reserve: Vulkan_Host compute buffer size = 28.26 MiB sched_reserve: graph: nodes = 1406, splits = 2, input objects = 4, input tensors = 6 sched_reserve: reserve took 50.35 ms, sched copies = 1 attach_threadpool: call set_n_threads: n_threads = 8, n_threads_batch = 8 state_read_meta: cell_count = 8192, dest_seq_id = 0 set_n_threads: n_threads = 8, n_threads_batch = 8 state_read_meta: cell_count = 8192, dest_seq_id = 0 set_n_threads: n_threads = 8, n_threads_batch = 8 state_read_meta: cell_count = 8192, dest_seq_id = 0 set_n_threads: n_threads = 8, n_threads_batch = 8 state_read_meta: cell_count = 8192, dest_seq_id = 0 set_n_threads: n_threads = 8, n_threads_batch = 8 state_read_meta: cell_count = 8192, dest_seq_id = 0 set_n_threads: n_threads = 8, n_threads_batch = 8 llama_perf_context_print: load time = 15137.95 ms llama_perf_context_print: prompt eval time = 0.00 ms / 1 tokens ( 0.00 ms per token, inf tokens per second) llama_perf_context_print: eval time = 0.00 ms / 641 runs ( 0.00 ms per token, inf tokens per second) llama_perf_context_print: total time = 26808.78 ms / 642 tokens llama_perf_context_print: graphs reused = 639 ~llama_context: Vulkan1 compute buffer size is 316.7500 MiB, matches expectation of 316.7500 MiB ~llama_context: Vulkan_Host compute buffer size is 28.2637 MiB, matches expectation of 28.2637 MiB