VLLM_USE_MODELSCOPE=True vllm serve openai-mirror/whisper-small --tensor_parallel_size 1 --enforce-eager --trust_remote_code & VLLM_USE_MODELSCOPE=True vllm serve openai-mirror/whisper-small --tensor_parallel_size 1 --trust_remote_code & 

INFO 08-04 02:16:27 [config.py:3440] Downcasting torch.float32 to torch.bfloat16. INFO 08-04 02:16:27 [config.py:1604] Using max model len 448 WARNING 08-04 02:16:27 [arg_utils.py:1690] ['WhisperForConditionalGeneration', 'TransformersForCausalLM'] is not supported by the V1 Engine. Falling back to V0. Traceback (most recent call last): File "/usr/local/python3.11.13/bin/vllm", line 8, in <module> sys.exit(main()) ^^^^^^ File "/vllm-workspace/vllm/vllm/entrypoints/cli/main.py", line 54, in main args.dispatch_function(args) File "/vllm-workspace/vllm/vllm/entrypoints/cli/serve.py", line 52, in cmd uvloop.run(run_server(args)) File "/usr/local/python3.11.13/lib/python3.11/site-packages/uvloop/__init__.py", line 105, in run return runner.run(wrapper()) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.13/lib/python3.11/asyncio/runners.py", line 118, in run return self._loop.run_until_complete(task) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete File "/usr/local/python3.11.13/lib/python3.11/site-packages/uvloop/__init__.py", line 61, in wrapper return await main ^^^^^^^^^^ File "/vllm-workspace/vllm/vllm/entrypoints/openai/api_server.py", line 1791, in run_server await run_server_worker(listen_address, sock, args, **uvicorn_kwargs) File "/vllm-workspace/vllm/vllm/entrypoints/openai/api_server.py", line 1811, in run_server_worker async with build_async_engine_client(args, client_config) as engine_client: File "/usr/local/python3.11.13/lib/python3.11/contextlib.py", line 210, in __aenter__ return await anext(self.gen) ^^^^^^^^^^^^^^^^^^^^^ File "/vllm-workspace/vllm/vllm/entrypoints/openai/api_server.py", line 158, in build_async_engine_client async with build_async_engine_client_from_engine_args( File "/usr/local/python3.11.13/lib/python3.11/contextlib.py", line 210, in __aenter__ return await anext(self.gen) ^^^^^^^^^^^^^^^^^^^^^ File "/vllm-workspace/vllm/vllm/entrypoints/openai/api_server.py", line 180, in build_async_engine_client_from_engine_args vllm_config = engine_args.create_engine_config(usage_context=usage_context) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/vllm-workspace/vllm/vllm/engine/arg_utils.py", line 1277, in create_engine_config config = VllmConfig( ^^^^^^^^^^^ File "/usr/local/python3.11.13/lib/python3.11/site-packages/pydantic/_internal/_dataclasses.py", line 123, in __init__ s.__pydantic_validator__.validate_python(ArgsKwargs(args, kwargs), self_instance=s) pydantic_core._pydantic_core.ValidationError: 1 validation error for VllmConfig Value error, vLLM Ascend does not support V0 engine. [type=value_error, input_value=ArgsKwargs((), {'model_co...additional_config': {}}), input_type=ArgsKwargs] For further information visit https://errors.pydantic.dev/2.11/v/value_error [ERROR] 2025-08-04-02:16:27 (PID:39324, Device:-1, RankID:-1) ERR99999 UNKNOWN applicaiton exception 

INFO 08-04 02:18:50 [config.py:3440] Downcasting torch.float32 to torch.bfloat16. INFO 08-04 02:18:50 [config.py:1604] Using max model len 448 WARNING 08-04 02:18:50 [arg_utils.py:1690] ['WhisperForConditionalGeneration', 'TransformersForCausalLM'] is not supported by the V1 Engine. Falling back to V0. Traceback (most recent call last): File "/usr/local/python3.11.13/bin/vllm", line 8, in <module> sys.exit(main()) ^^^^^^ File "/vllm-workspace/vllm/vllm/entrypoints/cli/main.py", line 54, in main args.dispatch_function(args) File "/vllm-workspace/vllm/vllm/entrypoints/cli/serve.py", line 52, in cmd uvloop.run(run_server(args)) File "/usr/local/python3.11.13/lib/python3.11/site-packages/uvloop/__init__.py", line 105, in run return runner.run(wrapper()) ^^^^^^^^^^^^^^^^^^^^^ File "/usr/local/python3.11.13/lib/python3.11/asyncio/runners.py", line 118, in run return self._loop.run_until_complete(task) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete File "/usr/local/python3.11.13/lib/python3.11/site-packages/uvloop/__init__.py", line 61, in wrapper return await main ^^^^^^^^^^ File "/vllm-workspace/vllm/vllm/entrypoints/openai/api_server.py", line 1791, in run_server await run_server_worker(listen_address, sock, args, **uvicorn_kwargs) File "/vllm-workspace/vllm/vllm/entrypoints/openai/api_server.py", line 1811, in run_server_worker async with build_async_engine_client(args, client_config) as engine_client: File "/usr/local/python3.11.13/lib/python3.11/contextlib.py", line 210, in __aenter__ return await anext(self.gen) ^^^^^^^^^^^^^^^^^^^^^ File "/vllm-workspace/vllm/vllm/entrypoints/openai/api_server.py", line 158, in build_async_engine_client async with build_async_engine_client_from_engine_args( File "/usr/local/python3.11.13/lib/python3.11/contextlib.py", line 210, in __aenter__ return await anext(self.gen) ^^^^^^^^^^^^^^^^^^^^^ File "/vllm-workspace/vllm/vllm/entrypoints/openai/api_server.py", line 180, in build_async_engine_client_from_engine_args vllm_config = engine_args.create_engine_config(usage_context=usage_context) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/vllm-workspace/vllm/vllm/engine/arg_utils.py", line 1277, in create_engine_config config = VllmConfig( ^^^^^^^^^^^ File "/usr/local/python3.11.13/lib/python3.11/site-packages/pydantic/_internal/_dataclasses.py", line 123, in __init__ s.__pydantic_validator__.validate_python(ArgsKwargs(args, kwargs), self_instance=s) pydantic_core._pydantic_core.ValidationError: 1 validation error for VllmConfig Value error, vLLM Ascend does not support V0 engine. [type=value_error, input_value=ArgsKwargs((), {'model_co...additional_config': {}}), input_type=ArgsKwargs] For further information visit https://errors.pydantic.dev/2.11/v/value_error