vllm - ✅(Solved) Fix [Bug]: Deepseek v3.2 RuntimeError: Worker failed with error "Assertion error" [2 pull requests, 1 participants]

vllm2026-04-06 05:36:01

ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

GitHub issue URL

Helpful · Quick feedback

GitHub stats

vllm-project/vllm#39057•Fetched 2026-04-08 02:52:45

View on GitHub

Comments

Participants

Timeline

Reactions

Author

jxdn

Participants

jxdn

Timeline (top)

labeled ×1

Error Message

(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] hidden_states, last_hidden_states = self.dummy_run( (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/utils/contextlib.py", line 124, in decorate_context (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return func(*args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/worker/gpu_model_runner.py", line 5477, in dummy_run (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] outputs = self.model( (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/cuda_graph.py", line 254, in call (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return self.runnable(*args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1776, in wrapped_call_impl (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return self.call_impl(*args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1787, in call_impl (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return forward_call(*args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/models/deepseek_v2.py", line 1430, in forward (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] hidden_states = self.model( (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/decorators.py", line 618, in call (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] output = self.aot_compiled_fn(self, *args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/dynamo/aot_compile.py", line 124, in call (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return self.fn(*args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/models/deepseek_v2.py", line 1224, in forward (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] def forward( (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/caching.py", line 211, in call (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return self.optimized_call(*args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/fx/graph_module.py", line 936, in call_wrapped (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return self.wrapped_call(self, *args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/fx/graph_module.py", line 455, in call (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] raise e (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/fx/graph_module.py", line 442, in call (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return super(self.cls, obj).call(*args, **kwargs) # type: ignore[misc] (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1776, in wrapped_call_impl (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return self.call_impl(*args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1787, in call_impl (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return forward_call(*args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "<eval_with_key>.372", line 1196, in forward (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] submod_4 = self.submod_4(getitem_7, s72, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_scale_inv, l_self_modules_layers_modules_0_modules_post_attention_layernorm_parameters_weight, getitem_8, l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight, l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_scale_inv, l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight, l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_scale_inv, l_self_modules_layers_modules_1_modules_input_layernorm_parameters_weight, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_scale_inv, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_a_layernorm_parameters_weight, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_kv_a_layernorm_parameters_weight_, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_rotary_emb_buffers_cos_sin_cache_, l_positions_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_weights_proj_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_bias_, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_indexer_rope_emb_buffers_cos_sin_cache_, getitem_9); getitem_7 = l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_ = l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_0_modules_post_attention_layernorm_parameters_weight_ = getitem_8 = l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_ = l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_ = l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_input_layernorm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_a_layernorm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_kv_a_layernorm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_weights_proj_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_bias_ = None (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/cuda_graph.py", line 254, in call (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return self.runnable(*args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/piecewise_backend.py", line 367, in call (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return range_entry.runnable(*args) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_inductor/standalone_compile.py", line 122, in call (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return self._compiled_fn(*args) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_dynamo/eval_frame.py", line 1181, in _fn (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return fn(*args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/aot_autograd.py", line 1148, in forward (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return compiled_fn(full_args) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 357, in runtime_wrapper (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] all_outs = call_func_at_runtime_with_args( (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/utils.py", line 134, in call_func_at_runtime_with_args (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] out = normalize_as_list(f(args)) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 1962, in call (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return self.compiled_fn(*args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 531, in wrapper (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return compiled_fn(runtime_args) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 729, in inner_fn (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] outs = compiled_fn(args) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_inductor/output_code.py", line 638, in call (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return self.current_callable(inputs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_inductor/utils.py", line 3220, in run (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] out = model(new_inputs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/tmp/torchinductor_mzidni/xe/cxez4622wlllvvnqqhof7jbkae2yblxvpgtcj5wzgodcbyjz6vsw.py", line 1875, in call (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] buf4 = torch.ops.vllm.flashinfer_fp8_blockscale_gemm.default(buf3, arg6_1, arg7_1, 128, True) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_ops.py", line 819, in call (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return self._op(*args, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/layers/quantization/utils/fp8_utils.py", line 318, in _flashinfer_fp8_blockscale_gemm_impl (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return torch.cond( (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_higher_order_ops/cond.py", line 186, in cond (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return false_fn(*operands) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/layers/quantization/utils/fp8_utils.py", line 300, in run_deepgemm (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] fp8_gemm_nt( (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/utils/deep_gemm.py", line 226, in fp8_gemm_nt (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] return _fp8_gemm_nt_impl(*args, disable_ue8m0_cast=not use_ue8m0, **kwargs) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] RuntimeError: CUDA driver error (csrc/apis/../jit_kernels/impls/../../jit/handle.hpp:83): 301 (CUDA_ERROR_FILE_NOT_FOUND, file not found) (Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] EngineCore failed to start. (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] Traceback (most recent call last): (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1074, in run_engine_core (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] engine_core = DPEngineCoreProc(*args, **kwargs) (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1609, in init (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] super().init( (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] return func(*args, **kwargs) (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^ (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 848, in init (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] super().init( (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 124, in init (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] kv_cache_config = self._initialize_kv_caches(vllm_config) (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] return func(*args, **kwargs) (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^ (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 247, in _initialize_kv_caches (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] available_gpu_memory = self.model_executor.determine_available_memory() (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/abstract.py", line 142, in determine_available_memory (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] return self.collective_rpc("determine_available_memory") (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 411, in collective_rpc (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] return future if non_block else future.result() (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] ^^^^^^^^^^^^^^^ (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 88, in result (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] return super().result() (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] ^^^^^^^^^^^^^^^^ (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 449, in result (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] return self.__get_result() (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] ^^^^^^^^^^^^^^^^^^^ (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] raise self._exception (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 92, in _wait_for_response (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] response = self.aggregate(self.get_response()) (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] ^^^^^^^^^^^^^^^^^^^ (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 398, in get_response (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] raise RuntimeError( (EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] RuntimeError: Worker failed with error 'CUDA driver error (csrc/apis/../jit_kernels/impls/../../jit/handle.hpp:83): 301 (CUDA_ERROR_FILE_NOT_FOUND, file not found)', please check the stack trace above for the root cause (Worker_DP5_EP5 pid=2198454) WARNING 04-06 13:20:34 [multiproc_executor.py:885] WorkerProc was terminated NVCC compilation failed: cc1plus: fatal error: /hpfs/mzidni/deep_gemm/cache/kernel.sm90_fp8_gemm_1d2d.7867d4d584e57d5eadffca2513e78c48/kernel.cu: No such file or directory compilation terminated.

(EngineCore_DP6 pid=2195264) ERROR 04-06 13:20:37 [multiproc_executor.py:291] Worker proc VllmWorker-0 died unexpectedly, shutting down executor. (EngineCore_DP6 pid=2195264) Process EngineCore_DP6: (EngineCore_DP6 pid=2195264) Traceback (most recent call last): (EngineCore_DP6 pid=2195264) File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap (EngineCore_DP6 pid=2195264) self.run() (EngineCore_DP6 pid=2195264) File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/multiprocessing/process.py", line 108, in run (EngineCore_DP6 pid=2195264) self._target(*self._args, **self._kwargs) (EngineCore_DP6 pid=2195264) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1112, in run_engine_core (EngineCore_DP6 pid=2195264) raise e (EngineCore_DP6 pid=2195264) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1074, in run_engine_core (EngineCore_DP6 pid=2195264) engine_core = DPEngineCoreProc(*args, **kwargs) (EngineCore_DP6 pid=2195264) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (EngineCore_DP6 pid=2195264) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1609, in init (EngineCore_DP6 pid=2195264) super().init( (EngineCore_DP6 pid=2195264) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper (EngineCore_DP6 pid=2195264) return func(*args, **kwargs) (EngineCore_DP6 pid=2195264) ^^^^^^^^^^^^^^^^^^^^^ (EngineCore_DP6 pid=2195264) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 848, in init (EngineCore_DP6 pid=2195264) super().init( (EngineCore_DP6 pid=2195264) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 124, in init (EngineCore_DP6 pid=2195264) kv_cache_config = self._initialize_kv_caches(vllm_config) (EngineCore_DP6 pid=2195264) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (EngineCore_DP6 pid=2195264) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper (EngineCore_DP6 pid=2195264) return func(*args, **kwargs) (EngineCore_DP6 pid=2195264) ^^^^^^^^^^^^^^^^^^^^^ (EngineCore_DP6 pid=2195264) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 247, in _initialize_kv_caches (EngineCore_DP6 pid=2195264) available_gpu_memory = self.model_executor.determine_available_memory() (EngineCore_DP6 pid=2195264) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (EngineCore_DP6 pid=2195264) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/abstract.py", line 142, in determine_available_memory (EngineCore_DP6 pid=2195264) return self.collective_rpc("determine_available_memory") (EngineCore_DP6 pid=2195264) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ (EngineCore_DP6 pid=2195264) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 411, in collective_rpc (EngineCore_DP6 pid=2195264) return future if non_block else future.result() (EngineCore_DP6 pid=2195264) ^^^^^^^^^^^^^^^ (EngineCore_DP6 pid=2195264) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 88, in result (EngineCore_DP6 pid=2195264) return super().result() (EngineCore_DP6 pid=2195264) ^^^^^^^^^^^^^^^^ (EngineCore_DP6 pid=2195264) File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 449, in result (EngineCore_DP6 pid=2195264) return self.__get_result() (EngineCore_DP6 pid=2195264) ^^^^^^^^^^^^^^^^^^^ (EngineCore_DP6 pid=2195264) File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result (EngineCore_DP6 pid=2195264) raise self._exception (EngineCore_DP6 pid=2195264) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 92, in _wait_for_response (EngineCore_DP6 pid=2195264) response = self.aggregate(self.get_response()) (EngineCore_DP6 pid=2195264) ^^^^^^^^^^^^^^^^^^^ (EngineCore_DP6 pid=2195264) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 398, in get_response (EngineCore_DP6 pid=2195264) raise RuntimeError( (EngineCore_DP6 pid=2195264) RuntimeError: Worker failed with error 'Assertion error (csrc/apis/../jit_kernels/impls/../../jit/compiler.hpp:178): false and "NVCC compilation failed"', please check the stack trace above for the root cause Traceback (most recent call last): File "/hpfs/mzidni/.venv/bin/vllm", line 10, in <module> sys.exit(main()) ^^^^^^ File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 75, in main args.dispatch_function(args) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 118, in cmd run_multi_api_server(args) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 279, in run_multi_api_server with launch_core_engines( ^^^^^^^^^^^^^^^^^^^^ File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/contextlib.py", line 144, in exit next(self.gen) File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 1073, in launch_core_engines wait_for_engine_startup( File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 1132, in wait_for_engine_startup raise RuntimeError( RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {}

Root Cause

error messages

(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     hidden_states, last_hidden_states = self._dummy_run(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                                         ^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 124, in decorate_context
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return func(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/worker/gpu_model_runner.py", line 5477, in _dummy_run
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     outputs = self.model(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]               ^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/cuda_graph.py", line 254, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.runnable(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._call_impl(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return forward_call(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/models/deepseek_v2.py", line 1430, in forward
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     hidden_states = self.model(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                     ^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/decorators.py", line 618, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     output = self.aot_compiled_fn(self, *args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_dynamo/aot_compile.py", line 124, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.fn(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/models/deepseek_v2.py", line 1224, in forward
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     def forward(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/caching.py", line 211, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.optimized_call(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/fx/graph_module.py", line 936, in call_wrapped
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._wrapped_call(self, *args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/fx/graph_module.py", line 455, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     raise e
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/fx/graph_module.py", line 442, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return super(self.cls, obj).__call__(*args, **kwargs)  # type: ignore[misc]
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._call_impl(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return forward_call(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "<eval_with_key>.372", line 1196, in forward
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     submod_4 = self.submod_4(getitem_7, s72, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_0_modules_post_attention_layernorm_parameters_weight_, getitem_8, l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_, l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_, l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_input_layernorm_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_a_layernorm_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_kv_a_layernorm_parameters_weight_, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_rotary_emb_buffers_cos_sin_cache_, l_positions_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_weights_proj_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_bias_, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_indexer_rope_emb_buffers_cos_sin_cache_, getitem_9);  getitem_7 = l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_ = l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_0_modules_post_attention_layernorm_parameters_weight_ = getitem_8 = l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_ = l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_ = l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_input_layernorm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_a_layernorm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_kv_a_layernorm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_weights_proj_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_bias_ = None
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/cuda_graph.py", line 254, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.runnable(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/piecewise_backend.py", line 367, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return range_entry.runnable(*args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_inductor/standalone_compile.py", line 122, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._compiled_fn(*args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_dynamo/eval_frame.py", line 1181, in _fn
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return fn(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/aot_autograd.py", line 1148, in forward
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return compiled_fn(full_args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 357, in runtime_wrapper
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     all_outs = call_func_at_runtime_with_args(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/utils.py", line 134, in call_func_at_runtime_with_args
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     out = normalize_as_list(f(args))
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                             ^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 1962, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.compiled_fn(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 531, in wrapper
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return compiled_fn(runtime_args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 729, in inner_fn
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     outs = compiled_fn(args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_inductor/output_code.py", line 638, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.current_callable(inputs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_inductor/utils.py", line 3220, in run
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     out = model(new_inputs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]           ^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/tmp/torchinductor_mzidni/xe/cxez4622wlllvvnqqhof7jbkae2yblxvpgtcj5wzgodcbyjz6vsw.py", line 1875, in call
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     buf4 = torch.ops.vllm.flashinfer_fp8_blockscale_gemm.default(buf3, arg6_1, arg7_1, 128, True)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_ops.py", line 819, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._op(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/layers/quantization/utils/fp8_utils.py", line 318, in _flashinfer_fp8_blockscale_gemm_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return torch.cond(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_higher_order_ops/cond.py", line 186, in cond
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return false_fn(*operands)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/layers/quantization/utils/fp8_utils.py", line 300, in run_deepgemm
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     fp8_gemm_nt(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/utils/deep_gemm.py", line 226, in fp8_gemm_nt
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return _fp8_gemm_nt_impl(*args, disable_ue8m0_cast=not use_ue8m0, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] RuntimeError: CUDA driver error (csrc/apis/../jit_kernels/impls/../../jit/handle.hpp:83): 301 (CUDA_ERROR_FILE_NOT_FOUND, file not found)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] 
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] EngineCore failed to start.
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] Traceback (most recent call last):
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1074, in run_engine_core
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     engine_core = DPEngineCoreProc(*args, **kwargs)
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1609, in __init__
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     super().__init__(
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return func(*args, **kwargs)
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 848, in __init__
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     super().__init__(
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 124, in __init__
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     kv_cache_config = self._initialize_kv_caches(vllm_config)
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return func(*args, **kwargs)
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 247, in _initialize_kv_caches
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     available_gpu_memory = self.model_executor.determine_available_memory()
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/abstract.py", line 142, in determine_available_memory
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return self.collective_rpc("determine_available_memory")
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 411, in collective_rpc
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return future if non_block else future.result()
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                                     ^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 88, in result
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return super().result()
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 449, in result
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return self.__get_result()
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     raise self._exception
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 92, in _wait_for_response
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     response = self.aggregate(self.get_response())
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                               ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 398, in get_response
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     raise RuntimeError(
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] RuntimeError: Worker failed with error 'CUDA driver error (csrc/apis/../jit_kernels/impls/../../jit/handle.hpp:83): 301 (CUDA_ERROR_FILE_NOT_FOUND, file not found)', please check the stack trace above for the root cause
(Worker_DP5_EP5 pid=2198454) WARNING 04-06 13:20:34 [multiproc_executor.py:885] WorkerProc was terminated
NVCC compilation failed: cc1plus: fatal error: /hpfs/mzidni/deep_gemm/cache/kernel.sm90_fp8_gemm_1d2d.7867d4d584e57d5eadffca2513e78c48/kernel.cu: No such file or directory
compilation terminated.

Fix Action

Fix / Workaround

============================== CPU Info

Architecture: x86_64 CPU op-mode(s): 32-bit, 64-bit Address sizes: 46 bits physical, 57 bits virtual Byte Order: Little Endian CPU(s): 112 On-line CPU(s) list: 0-111 Vendor ID: GenuineIntel Model name: Intel(R) Xeon(R) Platinum 8480+ CPU family: 6 Model: 143 Thread(s) per core: 1 Core(s) per socket: 56 Socket(s): 2 Stepping: 8 CPU(s) scaling MHz: 100% CPU max MHz: 3800.0000 CPU min MHz: 800.0000 BogoMIPS: 4000.00 Flags: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc art arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc cpuid aperfmperf tsc_known_freq pni pclmulqdq dtes64 monitor ds_cpl smx est tm2 ssse3 sdbg fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm 3dnowprefetch cpuid_fault epb cat_l3 cat_l2 cdp_l3 cdp_l2 ssbd mba ibrs ibpb stibp ibrs_enhanced fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid cqm rdt_a avx512f avx512dq rdseed adx smap avx512ifma clflushopt clwb intel_pt avx512cd sha_ni avx512bw avx512vl xsaveopt xsavec xgetbv1 xsaves cqm_llc cqm_occup_llc cqm_mbm_total cqm_mbm_local split_lock_detect avx_vnni avx512_bf16 wbnoinvd dtherm ida arat pln pts avx512vbmi umip pku ospke waitpkg avx512_vbmi2 gfni vaes vpclmulqdq avx512_vnni avx512_bitalg tme avx512_vpopcntdq la57 rdpid bus_lock_detect cldemote movdiri movdir64b enqcmd fsrm md_clear serialize tsxldtrk pconfig arch_lbr ibt amx_bf16 avx512_fp16 amx_tile amx_int8 flush_l1d arch_capabilities L1d cache: 5.3 MiB (112 instances) L1i cache: 3.5 MiB (112 instances) L2 cache: 224 MiB (112 instances) L3 cache: 210 MiB (2 instances) NUMA node(s): 2 NUMA node0 CPU(s): 0,2,4,6,8,10,12,14,16,18,20,22,24,26,28,30,32,34,36,38,40,42,44,46,48,50,52,54,56,58,60,62,64,66,68,70,72,74,76,78,80,82,84,86,88,90,92,94,96,98,100,102,104,106,108,110 NUMA node1 CPU(s): 1,3,5,7,9,11,13,15,17,19,21,23,25,27,29,31,33,35,37,39,41,43,45,47,49,51,53,55,57,59,61,63,65,67,69,71,73,75,77,79,81,83,85,87,89,91,93,95,97,99,101,103,105,107,109,111 Vulnerability Gather data sampling: Not affected Vulnerability Itlb multihit: Not affected Vulnerability L1tf: Not affected Vulnerability Mds: Not affected Vulnerability Meltdown: Not affected Vulnerability Mmio stale data: Not affected Vulnerability Retbleed: Not affected Vulnerability Spec rstack overflow: Not affected Vulnerability Spec store bypass: Mitigation; Speculative Store Bypass disabled via prctl Vulnerability Spectre v1: Mitigation; usercopy/swapgs barriers and __user pointer sanitization Vulnerability Spectre v2: Mitigation; Enhanced / Automatic IBRS, IBPB conditional, RSB filling, PBRSB-eIBRS SW sequence Vulnerability Srbds: Not affected Vulnerability Tsx async abort: Not affected

PR fix notes

PR #1132: test DeepGEMM Serialize concurrent JIT compilation per kernel

Repository: llm-d/llm-d
Author: Gregory-Pereira
State: open | merged: False
Link: https://github.com/llm-d/llm-d/pull/1132

Description (problem / solution / changelog)

cc @jxdn

Tests:

Changed files

docker/Dockerfile.cuda (modified, +4/-3)
docker/common-versions (modified, +2/-2)
docker/packages/cuda/runtime-packages.json (modified, +1/-0)

PR #302: Fix JIT cache race condition with multi-process compilation

Repository: deepseek-ai/DeepGEMM
Author: Gregory-Pereira
State: open | merged: False
Link: https://github.com/deepseek-ai/DeepGEMM/pull/302

Description (problem / solution / changelog)

addresses: #301

Changed files

csrc/jit/compiler.hpp (modified, +33/-0)

Code Example

(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     hidden_states, last_hidden_states = self._dummy_run(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                                         ^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 124, in decorate_context
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return func(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/worker/gpu_model_runner.py", line 5477, in _dummy_run
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     outputs = self.model(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]               ^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/cuda_graph.py", line 254, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.runnable(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._call_impl(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return forward_call(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/models/deepseek_v2.py", line 1430, in forward
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     hidden_states = self.model(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                     ^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/decorators.py", line 618, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     output = self.aot_compiled_fn(self, *args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_dynamo/aot_compile.py", line 124, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.fn(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/models/deepseek_v2.py", line 1224, in forward
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     def forward(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/caching.py", line 211, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.optimized_call(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/fx/graph_module.py", line 936, in call_wrapped
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._wrapped_call(self, *args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/fx/graph_module.py", line 455, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     raise e
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/fx/graph_module.py", line 442, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return super(self.cls, obj).__call__(*args, **kwargs)  # type: ignore[misc]
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._call_impl(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return forward_call(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "<eval_with_key>.372", line 1196, in forward
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     submod_4 = self.submod_4(getitem_7, s72, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_0_modules_post_attention_layernorm_parameters_weight_, getitem_8, l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_, l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_, l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_input_layernorm_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_a_layernorm_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_kv_a_layernorm_parameters_weight_, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_rotary_emb_buffers_cos_sin_cache_, l_positions_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_weights_proj_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_bias_, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_indexer_rope_emb_buffers_cos_sin_cache_, getitem_9);  getitem_7 = l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_ = l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_0_modules_post_attention_layernorm_parameters_weight_ = getitem_8 = l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_ = l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_ = l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_input_layernorm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_a_layernorm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_kv_a_layernorm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_weights_proj_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_bias_ = None
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/cuda_graph.py", line 254, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.runnable(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/piecewise_backend.py", line 367, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return range_entry.runnable(*args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_inductor/standalone_compile.py", line 122, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._compiled_fn(*args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_dynamo/eval_frame.py", line 1181, in _fn
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return fn(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/aot_autograd.py", line 1148, in forward
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return compiled_fn(full_args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 357, in runtime_wrapper
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     all_outs = call_func_at_runtime_with_args(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/utils.py", line 134, in call_func_at_runtime_with_args
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     out = normalize_as_list(f(args))
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                             ^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 1962, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.compiled_fn(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 531, in wrapper
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return compiled_fn(runtime_args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 729, in inner_fn
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     outs = compiled_fn(args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_inductor/output_code.py", line 638, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.current_callable(inputs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_inductor/utils.py", line 3220, in run
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     out = model(new_inputs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]           ^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/tmp/torchinductor_mzidni/xe/cxez4622wlllvvnqqhof7jbkae2yblxvpgtcj5wzgodcbyjz6vsw.py", line 1875, in call
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     buf4 = torch.ops.vllm.flashinfer_fp8_blockscale_gemm.default(buf3, arg6_1, arg7_1, 128, True)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_ops.py", line 819, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._op(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/layers/quantization/utils/fp8_utils.py", line 318, in _flashinfer_fp8_blockscale_gemm_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return torch.cond(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_higher_order_ops/cond.py", line 186, in cond
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return false_fn(*operands)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/layers/quantization/utils/fp8_utils.py", line 300, in run_deepgemm
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     fp8_gemm_nt(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/utils/deep_gemm.py", line 226, in fp8_gemm_nt
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return _fp8_gemm_nt_impl(*args, disable_ue8m0_cast=not use_ue8m0, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] RuntimeError: CUDA driver error (csrc/apis/../jit_kernels/impls/../../jit/handle.hpp:83): 301 (CUDA_ERROR_FILE_NOT_FOUND, file not found)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] 
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] EngineCore failed to start.
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] Traceback (most recent call last):
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1074, in run_engine_core
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     engine_core = DPEngineCoreProc(*args, **kwargs)
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1609, in __init__
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     super().__init__(
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return func(*args, **kwargs)
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 848, in __init__
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     super().__init__(
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 124, in __init__
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     kv_cache_config = self._initialize_kv_caches(vllm_config)
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return func(*args, **kwargs)
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 247, in _initialize_kv_caches
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     available_gpu_memory = self.model_executor.determine_available_memory()
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/abstract.py", line 142, in determine_available_memory
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return self.collective_rpc("determine_available_memory")
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 411, in collective_rpc
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return future if non_block else future.result()
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                                     ^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 88, in result
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return super().result()
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 449, in result
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return self.__get_result()
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     raise self._exception
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 92, in _wait_for_response
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     response = self.aggregate(self.get_response())
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                               ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 398, in get_response
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     raise RuntimeError(
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] RuntimeError: Worker failed with error 'CUDA driver error (csrc/apis/../jit_kernels/impls/../../jit/handle.hpp:83): 301 (CUDA_ERROR_FILE_NOT_FOUND, file not found)', please check the stack trace above for the root cause
(Worker_DP5_EP5 pid=2198454) WARNING 04-06 13:20:34 [multiproc_executor.py:885] WorkerProc was terminated
NVCC compilation failed: cc1plus: fatal error: /hpfs/mzidni/deep_gemm/cache/kernel.sm90_fp8_gemm_1d2d.7867d4d584e57d5eadffca2513e78c48/kernel.cu: No such file or directory
compilation terminated.

(EngineCore_DP6 pid=2195264) ERROR 04-06 13:20:37 [multiproc_executor.py:291] Worker proc VllmWorker-0 died unexpectedly, shutting down executor.
(EngineCore_DP6 pid=2195264) Process EngineCore_DP6:
(EngineCore_DP6 pid=2195264) Traceback (most recent call last):
(EngineCore_DP6 pid=2195264)   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap
(EngineCore_DP6 pid=2195264)     self.run()
(EngineCore_DP6 pid=2195264)   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/multiprocessing/process.py", line 108, in run
(EngineCore_DP6 pid=2195264)     self._target(*self._args, **self._kwargs)
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1112, in run_engine_core
(EngineCore_DP6 pid=2195264)     raise e
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1074, in run_engine_core
(EngineCore_DP6 pid=2195264)     engine_core = DPEngineCoreProc(*args, **kwargs)
(EngineCore_DP6 pid=2195264)                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1609, in __init__
(EngineCore_DP6 pid=2195264)     super().__init__(
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore_DP6 pid=2195264)     return func(*args, **kwargs)
(EngineCore_DP6 pid=2195264)            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 848, in __init__
(EngineCore_DP6 pid=2195264)     super().__init__(
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 124, in __init__
(EngineCore_DP6 pid=2195264)     kv_cache_config = self._initialize_kv_caches(vllm_config)
(EngineCore_DP6 pid=2195264)                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore_DP6 pid=2195264)     return func(*args, **kwargs)
(EngineCore_DP6 pid=2195264)            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 247, in _initialize_kv_caches
(EngineCore_DP6 pid=2195264)     available_gpu_memory = self.model_executor.determine_available_memory()
(EngineCore_DP6 pid=2195264)                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/abstract.py", line 142, in determine_available_memory
(EngineCore_DP6 pid=2195264)     return self.collective_rpc("determine_available_memory")
(EngineCore_DP6 pid=2195264)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 411, in collective_rpc
(EngineCore_DP6 pid=2195264)     return future if non_block else future.result()
(EngineCore_DP6 pid=2195264)                                     ^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 88, in result
(EngineCore_DP6 pid=2195264)     return super().result()
(EngineCore_DP6 pid=2195264)            ^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 449, in result
(EngineCore_DP6 pid=2195264)     return self.__get_result()
(EngineCore_DP6 pid=2195264)            ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
(EngineCore_DP6 pid=2195264)     raise self._exception
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 92, in _wait_for_response
(EngineCore_DP6 pid=2195264)     response = self.aggregate(self.get_response())
(EngineCore_DP6 pid=2195264)                               ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 398, in get_response
(EngineCore_DP6 pid=2195264)     raise RuntimeError(
(EngineCore_DP6 pid=2195264) RuntimeError: Worker failed with error 'Assertion error (csrc/apis/../jit_kernels/impls/../../jit/compiler.hpp:178): false and "NVCC compilation failed"', please check the stack trace above for the root cause
Traceback (most recent call last):
  File "/hpfs/mzidni/.venv/bin/vllm", line 10, in <module>
    sys.exit(main())
             ^^^^^^
  File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 75, in main
    args.dispatch_function(args)
  File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 118, in cmd
    run_multi_api_server(args)
  File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 279, in run_multi_api_server
    with launch_core_engines(
         ^^^^^^^^^^^^^^^^^^^^
  File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/contextlib.py", line 144, in __exit__
    next(self.gen)
  File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 1073, in launch_core_engines
    wait_for_engine_startup(
  File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 1132, in wait_for_engine_startup
    raise RuntimeError(
RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {}

RAW_BUFFERClick to expand / collapse

Your current environment

<details> <summary>The output of <code>python collect_env.py</code></summary>

Collecting environment information...

    System Info

============================== OS : Red Hat Enterprise Linux 9.4 (Plow) (x86_64) GCC version : (GCC) 13.1.0 Clang version : Could not collect CMake version : version 3.26.5 Libc version : glibc-2.34

============================== PyTorch Info

PyTorch version : 2.10.0+cu128 Is debug build : False CUDA used to build PyTorch : 12.8 ROCM used to build PyTorch : N/A

============================== Python Environment

Python version : 3.12.13 (main, Mar 24 2026, 22:49:22) [Clang 22.1.1 ] (64-bit runtime) Python platform : Linux-5.14.0-427.13.1.el9_4.x86_64-x86_64-with-glibc2.34

============================== CUDA / GPU Info

Is CUDA available : True CUDA runtime version : Could not collect CUDA_MODULE_LOADING set to : GPU models and configuration : GPU 0: NVIDIA H200 GPU 1: NVIDIA H200 GPU 2: NVIDIA H200 GPU 3: NVIDIA H200 GPU 4: NVIDIA H200 GPU 5: NVIDIA H200 GPU 6: NVIDIA H200 GPU 7: NVIDIA H200

Nvidia driver version : 575.57.08 cuDNN version : Could not collect HIP runtime version : N/A MIOpen runtime version : N/A Is XNNPACK available : True

============================== CPU Info

============================== Versions of relevant libraries

[pip3] flashinfer-python==0.6.7 [pip3] numpy==2.2.6 [pip3] nvidia-cublas-cu12==12.8.4.1 [pip3] nvidia-cuda-cupti-cu12==12.8.90 [pip3] nvidia-cuda-nvrtc-cu12==12.8.93 [pip3] nvidia-cuda-runtime-cu12==12.8.90 [pip3] nvidia-cudnn-cu12==9.10.2.21 [pip3] nvidia-cudnn-frontend==1.18.0 [pip3] nvidia-cufft-cu12==11.3.3.83 [pip3] nvidia-cufile-cu12==1.13.1.3 [pip3] nvidia-curand-cu12==10.3.9.90 [pip3] nvidia-cusolver-cu12==11.7.3.90 [pip3] nvidia-cusparse-cu12==12.5.8.93 [pip3] nvidia-cusparselt-cu12==0.7.1 [pip3] nvidia-cutlass-dsl==4.4.2 [pip3] nvidia-cutlass-dsl-libs-base==4.4.2 [pip3] nvidia-ml-py==13.595.45 [pip3] nvidia-nccl-cu12==2.27.5 [pip3] nvidia-nvjitlink-cu12==12.8.93 [pip3] nvidia-nvshmem-cu12==3.4.5 [pip3] nvidia-nvtx-cu12==12.8.90 [pip3] pyzmq==27.1.0 [pip3] torch==2.10.0 [pip3] torch_c_dlpack_ext==0.1.5 [pip3] torchaudio==2.10.0 [pip3] torchvision==0.25.0 [pip3] transformers==4.57.6 [pip3] triton==3.6.0 [conda] Could not collect

============================== vLLM Info

ROCM Version vLLM Version vLLM Build Flags: CUDA Archs: Not Set; ROCm: Disabled GPU Topology: GPU0 GPU1 GPU0 X GPU1 NV18 X GPU2 NV18 NV18 X GPU3 NV18 NV18 NV18 GPU4 NV18 GPU5 NV18 GPU6 NV18 GPU7 NV18 NIC0 PIX NIC1 NODE PIX NIC2 NODE NODE PIX NIC3 NODE NIC4 SYS NIC5 SYS NIC6 SYS NIC7 SYS NIC8 SYS NIC9 SYS : Could not collect : 0.19.1rc1.dev44+g780ba3745 (git sha: 780ba3745) GPU2 GPU3 GPU4 GPU5 GPU6 GPU7 NIC0 NIC1 NIC2 NIC3 NIC4 NIC5 NIC6 NIC7 NIC8 NIC9 CPU Affinity NUMA Affinity GPU NUMA ID NV18 NV18 NV18 NV18 NV18 NV18 NV18 PIX NODE NODE NODE SYS SYS SYS SYS SYS SYS 0,2,4,6,8,10 0 N/A NV18 NV18 NV18 NV18 NV18 NV18 NODE PIX NODE NODE SYS SYS SYS SYS SYS SYS 0,2,4,6,8,10 0 N/A NV18 NV18 NV18 NV18 NV18 NODE NODE PIX NODE SYS SYS SYS SYS SYS SYS 0,2,4,6,8,10 0 N/A X NV18 NV18 NV18 NV18 NODE NODE NODE PIX SYS SYS SYS SYS SYS SYS 0,2,4,6,8,10 0 N/A NV18 NV18 NV18 X NV18 NV18 NV18 SYS SYS SYS SYS PIX PIX PIX NODE NODE NODE 1,3,5,7,9,11 1 N/A NV18 NV18 NV18 NV18 X NV18 NV18 SYS SYS SYS SYS NODE NODE NODE PIX NODE NODE 1,3,5,7,9,11 1 N/A NV18 NV18 NV18 NV18 NV18 X NV18 SYS SYS SYS SYS NODE NODE NODE NODE PIX NODE 1,3,5,7,9,11 1 N/A NV18 NV18 NV18 NV18 NV18 NV18 X SYS SYS SYS SYS NODE NODE NODE NODE NODE PIX 1,3,5,7,9,11 1 N/A NODE NODE NODE SYS SYS SYS SYS X NODE NODE NODE SYS SYS SYS SYS SYS SYS NODE NODE SYS SYS SYS SYS NODE X NODE NODE SYS SYS SYS SYS SYS SYS NODE SYS SYS SYS SYS NODE NODE X NODE SYS SYS SYS SYS SYS SYS NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE X SYS SYS SYS SYS SYS SYS SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS X PIX PIX NODE NODE NODE SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS PIX X PIX NODE NODE NODE SYS SYS SYS PIX NODE NODE NODE SYS SYS SYS SYS PIX PIX X NODE NODE NODE SYS SYS SYS NODE PIX NODE NODE SYS SYS SYS SYS NODE NODE NODE X NODE NODE SYS SYS SYS NODE NODE PIX NODE SYS SYS SYS SYS NODE NODE NODE NODE X NODE SYS SYS SYS NODE NODE NODE PIX SYS SYS SYS SYS NODE NODE NODE NODE NODE X

Legend:

X = Self SYS = Connection traversing PCIe as well as the SMP interconnect between NUMA nodes (e.g., QPI/UPI) NODE = Connection traversing PCIe as well as the interconnect between PCIe Host Bridges within a NUMA node PHB = Connection traversing PCIe as well as a PCIe Host Bridge (typically the CPU) PXB = Connection traversing multiple PCIe bridges (without traversing the PCIe Host Bridge) PIX = Connection traversing at most a single PCIe bridge NV# = Connection traversing a bonded set of # NVLinks

NIC Legend:

NIC0: mlx5_0 NIC1: mlx5_1 NIC2: mlx5_2 NIC3: mlx5_3 NIC4: mlx5_4 NIC5: mlx5_5 NIC6: mlx5_6 NIC7: mlx5_7 NIC8: mlx5_8 NIC9: mlx5_9

============================== Environment Variables

LD_LIBRARY_PATH=/cm/local/apps/gcc/13.1.0/lib:/cm/local/apps/gcc/13.1.0/lib64:/cm/local/apps/gcc/13.1.0/lib32 VLLM_CACHE_ROOT=/hpfs/mzidni VLLM_RPC_TIMEOUT=300 PYTORCH_NVML_BASED_CUDA_CHECK=1 TORCHINDUCTOR_COMPILE_THREADS=1 TORCHINDUCTOR_CACHE_DIR=/tmp/torchinductor_mzidni

</details>

🐛 Describe the bug

run new deepseek but failed:

uv run vllm serve deepseek-ai/DeepSeek-V3.2 -dp 8 --enable-expert-parallel

how i build the environment:

https://github.com/vllm-project/recipes/blob/main/DeepSeek/DeepSeek-V3_2.md

error messages

(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     hidden_states, last_hidden_states = self._dummy_run(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                                         ^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/utils/_contextlib.py", line 124, in decorate_context
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return func(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/worker/gpu_model_runner.py", line 5477, in _dummy_run
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     outputs = self.model(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]               ^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/cuda_graph.py", line 254, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.runnable(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._call_impl(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return forward_call(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/models/deepseek_v2.py", line 1430, in forward
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     hidden_states = self.model(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                     ^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/decorators.py", line 618, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     output = self.aot_compiled_fn(self, *args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]              ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_dynamo/aot_compile.py", line 124, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.fn(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/models/deepseek_v2.py", line 1224, in forward
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     def forward(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/caching.py", line 211, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.optimized_call(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/fx/graph_module.py", line 936, in call_wrapped
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._wrapped_call(self, *args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/fx/graph_module.py", line 455, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     raise e
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/fx/graph_module.py", line 442, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return super(self.cls, obj).__call__(*args, **kwargs)  # type: ignore[misc]
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._call_impl(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return forward_call(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "<eval_with_key>.372", line 1196, in forward
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     submod_4 = self.submod_4(getitem_7, s72, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_0_modules_post_attention_layernorm_parameters_weight_, getitem_8, l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_, l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_, l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_input_layernorm_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_a_layernorm_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_kv_a_layernorm_parameters_weight_, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_rotary_emb_buffers_cos_sin_cache_, l_positions_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_scale_inv_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_weights_proj_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_weight_, l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_bias_, l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_indexer_rope_emb_buffers_cos_sin_cache_, getitem_9);  getitem_7 = l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_ = l_self_modules_layers_modules_0_modules_self_attn_modules_mla_attn_modules_o_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_0_modules_post_attention_layernorm_parameters_weight_ = getitem_8 = l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_ = l_self_modules_layers_modules_0_modules_mlp_modules_gate_up_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_ = l_self_modules_layers_modules_0_modules_mlp_modules_down_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_input_layernorm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_fused_qkv_a_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_a_layernorm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_q_b_proj_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_kv_a_layernorm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wq_b_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_wk_parameters_weight_scale_inv_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_weights_proj_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_weight_ = l_self_modules_layers_modules_1_modules_self_attn_modules_mla_attn_modules_indexer_modules_k_norm_parameters_bias_ = None
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/cuda_graph.py", line 254, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.runnable(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/compilation/piecewise_backend.py", line 367, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return range_entry.runnable(*args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_inductor/standalone_compile.py", line 122, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._compiled_fn(*args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_dynamo/eval_frame.py", line 1181, in _fn
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return fn(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/aot_autograd.py", line 1148, in forward
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return compiled_fn(full_args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 357, in runtime_wrapper
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     all_outs = call_func_at_runtime_with_args(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/utils.py", line 134, in call_func_at_runtime_with_args
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     out = normalize_as_list(f(args))
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]                             ^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 1962, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.compiled_fn(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 531, in wrapper
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return compiled_fn(runtime_args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_functorch/_aot_autograd/runtime_wrappers.py", line 729, in inner_fn
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     outs = compiled_fn(args)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_inductor/output_code.py", line 638, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self.current_callable(inputs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_inductor/utils.py", line 3220, in run
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     out = model(new_inputs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]           ^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/tmp/torchinductor_mzidni/xe/cxez4622wlllvvnqqhof7jbkae2yblxvpgtcj5wzgodcbyjz6vsw.py", line 1875, in call
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     buf4 = torch.ops.vllm.flashinfer_fp8_blockscale_gemm.default(buf3, arg6_1, arg7_1, 128, True)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_ops.py", line 819, in __call__
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return self._op(*args, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/layers/quantization/utils/fp8_utils.py", line 318, in _flashinfer_fp8_blockscale_gemm_impl
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return torch.cond(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/torch/_higher_order_ops/cond.py", line 186, in cond
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return false_fn(*operands)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/model_executor/layers/quantization/utils/fp8_utils.py", line 300, in run_deepgemm
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     fp8_gemm_nt(
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/utils/deep_gemm.py", line 226, in fp8_gemm_nt
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]     return _fp8_gemm_nt_impl(*args, disable_ue8m0_cast=not use_ue8m0, **kwargs)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] RuntimeError: CUDA driver error (csrc/apis/../jit_kernels/impls/../../jit/handle.hpp:83): 301 (CUDA_ERROR_FILE_NOT_FOUND, file not found)
(Worker_DP5_EP5 pid=2198454) ERROR 04-06 13:20:34 [multiproc_executor.py:963] 
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] EngineCore failed to start.
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] Traceback (most recent call last):
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1074, in run_engine_core
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     engine_core = DPEngineCoreProc(*args, **kwargs)
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1609, in __init__
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     super().__init__(
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return func(*args, **kwargs)
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 848, in __init__
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     super().__init__(
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 124, in __init__
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     kv_cache_config = self._initialize_kv_caches(vllm_config)
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return func(*args, **kwargs)
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 247, in _initialize_kv_caches
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     available_gpu_memory = self.model_executor.determine_available_memory()
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/abstract.py", line 142, in determine_available_memory
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return self.collective_rpc("determine_available_memory")
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 411, in collective_rpc
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return future if non_block else future.result()
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                                     ^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 88, in result
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return super().result()
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 449, in result
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     return self.__get_result()
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]            ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     raise self._exception
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 92, in _wait_for_response
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     response = self.aggregate(self.get_response())
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]                               ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 398, in get_response
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108]     raise RuntimeError(
(EngineCore_DP5 pid=2195263) ERROR 04-06 13:20:34 [core.py:1108] RuntimeError: Worker failed with error 'CUDA driver error (csrc/apis/../jit_kernels/impls/../../jit/handle.hpp:83): 301 (CUDA_ERROR_FILE_NOT_FOUND, file not found)', please check the stack trace above for the root cause
(Worker_DP5_EP5 pid=2198454) WARNING 04-06 13:20:34 [multiproc_executor.py:885] WorkerProc was terminated
NVCC compilation failed: cc1plus: fatal error: /hpfs/mzidni/deep_gemm/cache/kernel.sm90_fp8_gemm_1d2d.7867d4d584e57d5eadffca2513e78c48/kernel.cu: No such file or directory
compilation terminated.

(EngineCore_DP6 pid=2195264) ERROR 04-06 13:20:37 [multiproc_executor.py:291] Worker proc VllmWorker-0 died unexpectedly, shutting down executor.
(EngineCore_DP6 pid=2195264) Process EngineCore_DP6:
(EngineCore_DP6 pid=2195264) Traceback (most recent call last):
(EngineCore_DP6 pid=2195264)   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/multiprocessing/process.py", line 314, in _bootstrap
(EngineCore_DP6 pid=2195264)     self.run()
(EngineCore_DP6 pid=2195264)   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/multiprocessing/process.py", line 108, in run
(EngineCore_DP6 pid=2195264)     self._target(*self._args, **self._kwargs)
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1112, in run_engine_core
(EngineCore_DP6 pid=2195264)     raise e
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1074, in run_engine_core
(EngineCore_DP6 pid=2195264)     engine_core = DPEngineCoreProc(*args, **kwargs)
(EngineCore_DP6 pid=2195264)                   ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 1609, in __init__
(EngineCore_DP6 pid=2195264)     super().__init__(
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore_DP6 pid=2195264)     return func(*args, **kwargs)
(EngineCore_DP6 pid=2195264)            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 848, in __init__
(EngineCore_DP6 pid=2195264)     super().__init__(
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 124, in __init__
(EngineCore_DP6 pid=2195264)     kv_cache_config = self._initialize_kv_caches(vllm_config)
(EngineCore_DP6 pid=2195264)                       ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/tracing/otel.py", line 178, in sync_wrapper
(EngineCore_DP6 pid=2195264)     return func(*args, **kwargs)
(EngineCore_DP6 pid=2195264)            ^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/core.py", line 247, in _initialize_kv_caches
(EngineCore_DP6 pid=2195264)     available_gpu_memory = self.model_executor.determine_available_memory()
(EngineCore_DP6 pid=2195264)                            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/abstract.py", line 142, in determine_available_memory
(EngineCore_DP6 pid=2195264)     return self.collective_rpc("determine_available_memory")
(EngineCore_DP6 pid=2195264)            ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 411, in collective_rpc
(EngineCore_DP6 pid=2195264)     return future if non_block else future.result()
(EngineCore_DP6 pid=2195264)                                     ^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 88, in result
(EngineCore_DP6 pid=2195264)     return super().result()
(EngineCore_DP6 pid=2195264)            ^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 449, in result
(EngineCore_DP6 pid=2195264)     return self.__get_result()
(EngineCore_DP6 pid=2195264)            ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/concurrent/futures/_base.py", line 401, in __get_result
(EngineCore_DP6 pid=2195264)     raise self._exception
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 92, in _wait_for_response
(EngineCore_DP6 pid=2195264)     response = self.aggregate(self.get_response())
(EngineCore_DP6 pid=2195264)                               ^^^^^^^^^^^^^^^^^^^
(EngineCore_DP6 pid=2195264)   File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/executor/multiproc_executor.py", line 398, in get_response
(EngineCore_DP6 pid=2195264)     raise RuntimeError(
(EngineCore_DP6 pid=2195264) RuntimeError: Worker failed with error 'Assertion error (csrc/apis/../jit_kernels/impls/../../jit/compiler.hpp:178): false and "NVCC compilation failed"', please check the stack trace above for the root cause
Traceback (most recent call last):
  File "/hpfs/mzidni/.venv/bin/vllm", line 10, in <module>
    sys.exit(main())
             ^^^^^^
  File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/entrypoints/cli/main.py", line 75, in main
    args.dispatch_function(args)
  File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 118, in cmd
    run_multi_api_server(args)
  File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/entrypoints/cli/serve.py", line 279, in run_multi_api_server
    with launch_core_engines(
         ^^^^^^^^^^^^^^^^^^^^
  File "/home/mzidni/.local/share/uv/python/cpython-3.12.13-linux-x86_64-gnu/lib/python3.12/contextlib.py", line 144, in __exit__
    next(self.gen)
  File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 1073, in launch_core_engines
    wait_for_engine_startup(
  File "/hpfs/mzidni/.venv/lib/python3.12/site-packages/vllm/v1/engine/utils.py", line 1132, in wait_for_engine_startup
    raise RuntimeError(
RuntimeError: Engine core initialization failed. See root cause above. Failed core proc(s): {}

Before submitting a new issue...

Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

extent analysis

TL;DR

The issue is likely due to a CUDA driver error, specifically a file not found error, which is causing the NVCC compilation to fail.

Guidance

Check CUDA installation: Verify that CUDA is properly installed and configured on the system. Ensure that the CUDA version matches the one used to build PyTorch.
Verify NVCC compilation: Check the NVCC compilation logs to identify the specific file that is not found. This might indicate a missing dependency or incorrect path.
Environment variables: Review the environment variables, such as LD_LIBRARY_PATH, to ensure that they are correctly set and point to the right locations.
PyTorch and dependency versions: Confirm that PyTorch and its dependencies, including CUDA and cuDNN, are compatible and up-to-date.

Example

No specific code example is provided as the issue seems to be related to the environment and CUDA configuration rather than a code snippet.

Notes

The error message suggests a CUDA driver error, which might be related to the system configuration or the PyTorch build. It's essential to verify the CUDA installation, NVCC compilation, and environment variables to resolve the issue.

Recommendation

Apply a workaround by reconfiguring the CUDA environment or updating the PyTorch version to ensure compatibility with the system's CUDA installation. If the issue persists, consider seeking further assistance from the PyTorch or CUDA community.

Vote matrix · Quick signals

Works

Did the solution work? Tap to confirm.

Easy Fix

Was it a quick fix?

Time Saver

Did it save you time?

Blocking

Was it severely blocking?

Common Issue

Are others likely hitting this too?

Flaky / Intermittent

Is it intermittent?

Verified / Reproducible

Can you reproduce it reliably?

#api #environment variable #file not found #serialization error #model compatibility

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

vllm - ✅(Solved) Fix [Bug]: Deepseek v3.2 RuntimeError: Worker failed with error "Assertion error" [2 pull requests, 1 participants]

Recommended Tools

GitHub issue graph ai analysis

Error Message

Root Cause

Fix Action

Fix / Workaround

============================== CPU Info

PR fix notes

PR #1132: test DeepGEMM Serialize concurrent JIT compilation per kernel

Description (problem / solution / changelog)

Changed files

PR #302: Fix JIT cache race condition with multi-process compilation

Description (problem / solution / changelog)

Changed files

Code Example

Your current environment

Collecting environment information...

============================== PyTorch Info

============================== Python Environment

============================== CUDA / GPU Info

============================== CPU Info

============================== Versions of relevant libraries

============================== vLLM Info

============================== Environment Variables

🐛 Describe the bug

Before submitting a new issue...

extent analysis

TL;DR

Guidance

Example

Notes

Recommendation

Still need to ship something?

RELATED_DISCOVERY

TRENDING