API tools faq
paste
Guest User

vllm crash docker - gpt-oss-20b on RTX5090

a guest
Aug 12th, 2025
23
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
text 13.89 KB | None | 0 0
raw download clone embed print report
  1. INFO 08-12 14:36:59 [__init__.py:241] Automatically detected platform cuda.
  2. ESC[1;36m(APIServer pid=1)ESC[0;0m INFO 08-12 14:37:01 [api_server.py:1787] vLLM API server version 0.10.2.dev2+gf5635d62e.d20250807
  3. ESC[1;36m(APIServer pid=1)ESC[0;0m INFO 08-12 14:37:01 [utils.py:326] non-default args: {'model': 'openai/gpt-oss-20b', 'async_scheduling': True}
  4. ESC[1;36m(APIServer pid=1)ESC[0;0m INFO 08-12 14:37:09 [config.py:726] Resolved architecture: GptOssForCausalLM
  5. ESC[1;36m(APIServer pid=1)ESC[0;0m INFO 08-12 14:37:10 [config.py:1759] Using max model len 131072
  6. ESC[1;36m(APIServer pid=1)ESC[0;0m WARNING 08-12 14:37:12 [config.py:1198] mxfp4 quantization is not fully optimized yet. The speed can be slower than non-quantized models.
  7. ESC[1;36m(APIServer pid=1)ESC[0;0m INFO 08-12 14:37:13 [arg_utils.py:1188] Using mp-based distributed executor backend for async scheduling.
  8. ESC[1;36m(APIServer pid=1)ESC[0;0m INFO 08-12 14:37:13 [config.py:2588] Chunked prefill is enabled with max_num_batched_tokens=2048.
  9. ESC[1;36m(APIServer pid=1)ESC[0;0m INFO 08-12 14:37:13 [config.py:244] Overriding cuda graph sizes to [1, 2, 4, 8, 16, 24, 32, 40, 48, 56, 64, 72, 80, 88, 96, 104, 112, 120, 128, 136, 144, 152, 160, 168, 176, 184, 192, 200, 208, 216, 224, 232, 240, 248
  10. , 256, 272, 288, 304, 320, 336, 352, 368, 384, 400, 416, 432, 448, 464, 480, 496, 512, 528, 544, 560, 576, 592, 608, 624, 640, 656, 672, 688, 704, 720, 736, 752, 768, 784, 800, 816, 832, 848, 864, 880, 896, 912, 928, 944, 960, 976, 992, 1008, 1024]
  11. INFO 08-12 14:37:18 [__init__.py:241] Automatically detected platform cuda.
  12. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m INFO 08-12 14:37:21 [core.py:654] Waiting for init message from front-end.
  13. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m INFO 08-12 14:37:21 [core.py:73] Initializing a V1 LLM engine (v0.10.2.dev2+gf5635d62e.d20250807) with config: model='openai/gpt-oss-20b', speculative_config=None, tokenizer='openai/gpt-oss-20b', skip_tokenizer_i
  14. nit=False, tokenizer_mode=auto, revision=None, override_neuron_config={}, tokenizer_revision=None, trust_remote_code=False, dtype=torch.bfloat16, max_seq_len=131072, download_dir=None, load_format=auto, tensor_parallel_size=1, pipeline_parallel_size=1,
  15. disable_custom_all_reduce=False, quantization=mxfp4, enforce_eager=False, kv_cache_dtype=auto, device_config=cuda, decoding_config=DecodingConfig(backend='auto', disable_fallback=False, disable_any_whitespace=False, disable_additional_properties=False
  16. , reasoning_backend='openai'), observability_config=ObservabilityConfig(show_hidden_metrics_for_version=None, otlp_traces_endpoint=None, collect_detailed_traces=None), seed=0, served_model_name=openai/gpt-oss-20b, num_scheduler_steps=1, multi_step_stre
  17. am_outputs=True, enable_prefix_caching=True, chunked_prefill_enabled=True, use_async_output_proc=True, pooler_config=None, compilation_config={"level":3,"debug_dump_path":"","cache_dir":"","backend":"","custom_ops":[],"splitting_ops":["vllm.unified_att
  18. ention","vllm.unified_attention_with_output","vllm.mamba_mixer2"],"use_inductor":true,"compile_sizes":[],"inductor_compile_config":{"enable_auto_functionalized_v2":false},"inductor_passes":{},"use_cudagraph":true,"cudagraph_num_of_warmups":1,"cudagraph
  19. _capture_sizes":[1024,1008,992,976,960,944,928,912,896,880,864,848,832,816,800,784,768,752,736,720,704,688,672,656,640,624,608,592,576,560,544,528,512,496,480,464,448,432,416,400,384,368,352,336,320,304,288,272,256,248,240,232,224,216,208,200,192,184,1
  20. 76,168,160,152,144,136,128,120,112,104,96,88,80,72,64,56,48,40,32,24,16,8,4,2,1],"cudagraph_copy_inputs":false,"full_cuda_graph":false,"max_capture_size":1024,"local_cache_dir":null}
  21. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m
  22. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m LL LL MMM MMM
  23. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m LL LL MMMM MMMM
  24. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m V LL LL MM MM MM MM
  25. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m vvvv VVVV LL LL MM MM MM MM
  26. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m vvvv VVVV LL LL MM MMM MM
  27. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m vvv VVVV LL LL MM M MM
  28. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m vvVVVV LL LL MM MM
  29. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m VVVV LLLLLLLLLL LLLLLLLLL M M
  30. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m
  31. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m WARNING 08-12 14:37:21 [multiproc_worker_utils.py:273] Reducing Torch parallelism from 12 threads to 1 to avoid unnecessary CPU contention. Set OMP_NUM_THREADS in the external environment to tune this value as needed.
  32. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m INFO 08-12 14:37:21 [shm_broadcast.py:289] vLLM message queue communication handle: Handle(local_reader_ranks=[0], buffer_handle=(1, 16777216, 10, 'psm_06e2e7a6'), local_subscribe_addr='ipc:///tmp/5e7288cc-bd69-4452-95a9-13abc615ea70', remote_subscribe_addr=None, remote_addr_ipv6=False)
  33. INFO 08-12 14:37:24 [__init__.py:241] Automatically detected platform cuda.
  34. ESC[1;36m(VllmWorker pid=168)ESC[0;0m INFO 08-12 14:37:27 [shm_broadcast.py:289] vLLM message queue communication handle: Handle(local_reader_ranks=[0], buffer_handle=(1, 10485760, 10, 'psm_1ccdd475'), local_subscribe_addr='ipc:///tmp/9c1253c1-33f9-4b39-8f67-f99e7dbc5f86', remote_subscribe_addr=None, remote_addr_ipv6=False)
  35. [Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
  36. [Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
  37. [Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
  38. [Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
  39. [Gloo] Rank 0 is connected to 0 peer ranks. Expected number of connected peer ranks is : 0
  40. ESC[1;36m(VllmWorker pid=168)ESC[0;0m INFO 08-12 14:37:28 [parallel_state.py:1102] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, TP rank 0, EP rank 0
  41. ESC[1;36m(VllmWorker pid=168)ESC[0;0m INFO 08-12 14:37:28 [topk_topp_sampler.py:49] Using FlashInfer for top-p & top-k sampling.
  42. ESC[1;36m(VllmWorker pid=168)ESC[0;0m INFO 08-12 14:37:28 [gpu_model_runner.py:1913] Starting to load model openai/gpt-oss-20b...
  43. ESC[1;36m(VllmWorker pid=168)ESC[0;0m INFO 08-12 14:37:28 [gpu_model_runner.py:1945] Loading model from scratch...
  44. ESC[1;36m(VllmWorker pid=168)ESC[0;0m INFO 08-12 14:37:28 [cuda.py:286] Using Triton backend on V1 engine.
  45. ESC[1;36m(VllmWorker pid=168)ESC[0;0m WARNING 08-12 14:37:28 [rocm.py:29] Failed to import from amdsmi with ModuleNotFoundError("No module named 'amdsmi'")
  46. ESC[1;36m(VllmWorker pid=168)ESC[0;0m WARNING 08-12 14:37:28 [rocm.py:40] Failed to import from vllm._rocm_C with ModuleNotFoundError("No module named 'vllm._rocm_C'")
  47. ESC[1;36m(VllmWorker pid=168)ESC[0;0m INFO 08-12 14:37:28 [triton_attn.py:263] Using vllm unified attention for TritonAttentionImpl
  48. ESC[1;36m(VllmWorker pid=168)ESC[0;0m INFO 08-12 14:37:29 [weight_utils.py:296] Using model weights format ['*.safetensors']
  49. ESC[1;36m(VllmWorker pid=168)ESC[0;0m INFO 08-12 14:37:32 [default_loader.py:262] Loading weights took 3.18 seconds
  50. ESC[1;36m(VllmWorker pid=168)ESC[0;0m INFO 08-12 14:37:32 [mxfp4.py:176] Shuffling MoE weights, it might take a while...
  51. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] WorkerProc failed to start.
  52. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] Traceback (most recent call last):
  53. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/multiproc_executor.py", line 533, in worker_main
  54. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] worker = WorkerProc(*args, **kwargs)
  55. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  56. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/multiproc_executor.py", line 402, in __init__
  57. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] self.worker.load_model()
  58. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_worker.py", line 211, in load_model
  59. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] self.model_runner.load_model(eep_scale_up=eep_scale_up)
  60. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/worker/gpu_model_runner.py", line 1946, in load_model
  61. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] self.model = model_loader.load_model(
  62. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] ^^^^^^^^^^^^^^^^^^^^^^^^
  63. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/model_loader/base_loader.py", line 50, in load_model
  64. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] process_weights_after_loading(model, model_config, target_device)
  65. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/model_loader/utils.py", line 112, in process_weights_after_loading
  66. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] quant_method.process_weights_after_loading(module)
  67. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] File "/usr/local/lib/python3.12/dist-packages/vllm/model_executor/layers/quantization/mxfp4.py", line 260, in process_weights_after_loading
  68. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] shuffle_matrix_a(w13_bias[i].clone().reshape(-1, 1),
  69. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] ^^^^^^^^^^^^^^^^^^^
  70. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] torch.AcceleratorError: CUDA error: no kernel image is available for execution on the device
  71. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] Search for `cudaErrorNoKernelImageForDevice' in https://docs.nvidia.com/cuda/cuda-runtime-api/group__CUDART__TYPES.html for more information.
  72. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] CUDA kernel errors might be asynchronously reported at some other API call, so the stacktrace below might be incorrect.
  73. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] For debugging consider passing CUDA_LAUNCH_BLOCKING=1
  74. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559] Compile with `TORCH_USE_CUDA_DSA` to enable device-side assertions.
  75. ESC[1;36m(VllmWorker pid=168)ESC[0;0m ERROR 08-12 14:37:42 [multiproc_executor.py:559]
  76. ESC[1;36m(VllmWorker pid=168)ESC[0;0m INFO 08-12 14:37:42 [multiproc_executor.py:520] Parent process exited, terminating worker
  77. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] EngineCore failed to start.
  78. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] Traceback (most recent call last):
  79. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 709, in run_engine_core
  80. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] engine_core = EngineCoreProc(*args, **kwargs)
  81. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  82. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 510, in __init__
  83. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] super().__init__(vllm_config, executor_class, log_stats,
  84. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/engine/core.py", line 82, in __init__
  85. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] self.model_executor = executor_class(vllm_config)
  86. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  87. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] File "/usr/local/lib/python3.12/dist-packages/vllm/executor/executor_base.py", line 54, in __init__
  88. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] self._init_executor()
  89. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/multiproc_executor.py", line 96, in _init_executor
  90. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] self.workers = WorkerProc.wait_for_ready(unready_workers)
  91. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  92. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] File "/usr/local/lib/python3.12/dist-packages/vllm/v1/executor/multiproc_executor.py", line 472, in wait_for_ready
  93. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] raise e from None
  94. ESC[1;36m(EngineCore_0 pid=114)ESC[0;0m ERROR 08-12 14:37:44 [core.py:718] Exception: WorkerProc initialization failed due to an exception in a background process. See stack trace for root cause.
Advertisement
Add Comment
Please, Sign In to add comment
Public Pastes
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!