Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- release that supports one of these CUDA versions: 12.8, 13.0
- (EngineCore pid=44608) _warn_unsupported_code(d, device_cc, code_ccs)
- (EngineCore pid=44608) C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\torch\cuda\__init__.py:489: UserWarning:
- (EngineCore pid=44608) NVIDIA GeForce RTX 5090 with CUDA capability sm_120 is not compatible with the current PyTorch installation.
- (EngineCore pid=44608) The current PyTorch install supports CUDA capabilities sm_50 sm_60 sm_61 sm_70 sm_75 sm_80 sm_86 sm_90.
- (EngineCore pid=44608) If you want to use the NVIDIA GeForce RTX 5090 GPU with PyTorch, please check the instructions at https://pytorch.org/get-started/locally/
- (EngineCore pid=44608)
- (EngineCore pid=44608) queued_call()
- (EngineCore pid=44608) INFO 05-02 18:19:57 [registry.py:126] All limits of multimodal modalities supported by the model are set to 0, running in text-only mode.
- (EngineCore pid=44608) INFO 05-02 18:19:57 [parallel_state.py:1455] world_size=1 rank=0 local_rank=0 distributed_init_method=tcp://192.168.2.18:52901 backend=gloo
- [W502 18:19:57.000000000 socket.cpp:764] [c10d] The client socket has failed to connect to [WoodyhoNeo]:52901 (system error: 10049 - The requested address is not valid in its context.).
- (EngineCore pid=44608) INFO 05-02 18:19:57 [parallel_state.py:1767] rank 0 in world size 1 is assigned as DP rank 0, PP rank 0, PCP rank 0, TP rank 0, EP rank N/A, EPLB rank N/A
- (EngineCore pid=44608) Failed to get device capability: SM 12.x requires CUDA >= 12.9.
- (EngineCore pid=44608) Failed to get device capability: SM 12.x requires CUDA >= 12.9.
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] EngineCore failed to start.
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] Traceback (most recent call last):
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 1082, in run_engine_core
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] engine_core = EngineCoreProc(*args, engine_index=dp_rank, **kwargs)
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\tracing\otel.py", line 178, in sync_wrapper
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] return func(*args, **kwargs)
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 848, in __init__
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] super().__init__(
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 114, in __init__
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] self.model_executor = executor_class(vllm_config)
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\tracing\otel.py", line 178, in sync_wrapper
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] return func(*args, **kwargs)
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\executor\abstract.py", line 109, in __init__
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] self._init_executor()
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\executor\uniproc_executor.py", line 47, in _init_executor
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] self.driver_worker.init_device()
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\worker\worker_base.py", line 312, in init_device
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] self.worker.init_device() # type: ignore
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\tracing\otel.py", line 178, in sync_wrapper
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] return func(*args, **kwargs)
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\worker\gpu_worker.py", line 311, in init_device
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] self.model_runner = GPUModelRunnerV1(self.vllm_config, self.device)
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\worker\gpu_model_runner.py", line 480, in __init__
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] self.sampler = Sampler(logprobs_mode=self.model_config.logprobs_mode)
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\sample\sampler.py", line 64, in __init__
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] self.topk_topp_sampler = TopKTopPSampler(logprobs_mode)
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\sample\ops\topk_topp_sampler.py", line 40, in __init__
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] from vllm.v1.attention.backends.flashinfer import FlashInferBackend
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\attention\backends\flashinfer.py", line 11, in <module>
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] from flashinfer import (
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\flashinfer\__init__.py", line 24, in <module>
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] from . import jit as jit
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\flashinfer\jit\__init__.py", line 125, in <module>
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] raise ValueError(
- (EngineCore pid=44608) ERROR 05-02 18:19:58 [core.py:1108] ValueError: CUDA_LIB_PATH is not set. CUDA_LIB_PATH need to be set with the absolute path to CUDA root folder on Windows (for example, set CUDA_LIB_PATH=C:\CUDA\v12.4)
- (EngineCore pid=44608) Process EngineCore:
- (EngineCore pid=44608) Traceback (most recent call last):
- (EngineCore pid=44608) File "multiprocessing\process.py", line 314, in _bootstrap
- (EngineCore pid=44608) File "multiprocessing\process.py", line 108, in run
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 1112, in run_engine_core
- (EngineCore pid=44608) raise e
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 1082, in run_engine_core
- (EngineCore pid=44608) engine_core = EngineCoreProc(*args, engine_index=dp_rank, **kwargs)
- (EngineCore pid=44608) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\tracing\otel.py", line 178, in sync_wrapper
- (EngineCore pid=44608) return func(*args, **kwargs)
- (EngineCore pid=44608) ^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 848, in __init__
- (EngineCore pid=44608) super().__init__(
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\engine\core.py", line 114, in __init__
- (EngineCore pid=44608) self.model_executor = executor_class(vllm_config)
- (EngineCore pid=44608) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\tracing\otel.py", line 178, in sync_wrapper
- (EngineCore pid=44608) return func(*args, **kwargs)
- (EngineCore pid=44608) ^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\executor\abstract.py", line 109, in __init__
- (EngineCore pid=44608) self._init_executor()
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\executor\uniproc_executor.py", line 47, in _init_executor
- (EngineCore pid=44608) self.driver_worker.init_device()
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\worker\worker_base.py", line 312, in init_device
- (EngineCore pid=44608) self.worker.init_device() # type: ignore
- (EngineCore pid=44608) ^^^^^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\tracing\otel.py", line 178, in sync_wrapper
- (EngineCore pid=44608) return func(*args, **kwargs)
- (EngineCore pid=44608) ^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\worker\gpu_worker.py", line 311, in init_device
- (EngineCore pid=44608) self.model_runner = GPUModelRunnerV1(self.vllm_config, self.device)
- (EngineCore pid=44608) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\worker\gpu_model_runner.py", line 480, in __init__
- (EngineCore pid=44608) self.sampler = Sampler(logprobs_mode=self.model_config.logprobs_mode)
- (EngineCore pid=44608) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\sample\sampler.py", line 64, in __init__
- (EngineCore pid=44608) self.topk_topp_sampler = TopKTopPSampler(logprobs_mode)
- (EngineCore pid=44608) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\sample\ops\topk_topp_sampler.py", line 40, in __init__
- (EngineCore pid=44608) from vllm.v1.attention.backends.flashinfer import FlashInferBackend
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\vllm\v1\attention\backends\flashinfer.py", line 11, in <module>
- (EngineCore pid=44608) from flashinfer import (
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\flashinfer\__init__.py", line 24, in <module>
- (EngineCore pid=44608) from . import jit as jit
- (EngineCore pid=44608) File "C:\_vLLM\qwen3.6-windows-server\python\Lib\site-packages\flashinfer\jit\__init__.py", line 125, in <module>
- (EngineCore pid=44608) raise ValueError(
- (EngineCore pid=44608) ValueError: CUDA_LIB_PATH is not set. CUDA_LIB_PATH need to be set with the absolute path to CUDA root folder on Windows (for example, set CUDA_LIB_PATH=C:\CUDA\v12.4)
Advertisement
Add Comment
Please, Sign In to add comment