search

MeetKai / functionary

Chat language model that can use tools and interpret the results
MIT License
1.37k stars 107 forks source link

vllm.engine.async_llm_engine.AsyncEngineDeadError: Task finished unexpectedly. This should never happen! Please open an issue on Github. See stack trace above for the actual cause. #96

Open xiechengmude opened 8 months ago

xiechengmude commented 8 months ago

`_requests_in_progress = await self.engine_step() File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/engine/async_llm_engine.py", line 338, in engine_step request_outputs = await self.engine.step_async() File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/engine/async_llm_engine.py", line 191, in step_async output = await self._run_workers_async( File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/engine/async_llm_engine.py", line 219, in _run_workers_async all_outputs = await asyncio.gather(coros) File "/root/miniconda3/envs/agent/lib/python3.10/asyncio/tasks.py", line 650, in _wrap_awaitable return (yield from awaitable.await()) ray.exceptions.RayTaskError(RuntimeError): ray::RayWorkerVllm.execute_method() (pid=954874, ip=10.19.23.192, actor_id=67ba2e9c25498a976914e72a01000000, repr=<vllm.engine.ray_utils.RayWorkerVllm object at 0x7f25b2710e80>) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/engine/ray_utils.py", line 31, in execute_method return executor(args, kwargs) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(*args, *kwargs) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/worker/worker.py", line 159, in execute_model output = self.model_runner.execute_model(seq_group_metadata_list, File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/torch/utils/_contextlib.py", line 115, in decorate_context return func(args, kwargs) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/worker/model_runner.py", line 354, in execute_model output = self.model.sample( File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/model_executor/models/llama.py", line 295, in sample next_tokens = self.sampler(self.lm_head.weight, hidden_states, File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1518, in _wrapped_call_impl return self._call_impl(*args, *kwargs) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1527, in _call_impl return forward_call(args, **kwargs) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/model_executor/layers/sampler.py", line 92, in forward prompt_logprobs, sample_logprobs = _get_logprobs( File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/model_executor/layers/sampler.py", line 487, in _get_logprobs top_logprobs, top_token_ids = torch.topk(logprobs, RuntimeError: selected index k out of range

The above exception was the direct cause of the following exception:

Traceback (most recent call last): File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/uvicorn/protocols/http/httptools_impl.py", line 426, in run_asgi result = await app( # type: ignore[func-returns-value] File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 84, in call return await self.app(scope, receive, send) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/fastapi/applications.py", line 1106, in call await super().call(scope, receive, send) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/starlette/applications.py", line 122, in call await self.middleware_stack(scope, receive, send) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/starlette/middleware/errors.py", line 184, in call raise exc File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/starlette/middleware/errors.py", line 162, in call await self.app(scope, receive, _send) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/starlette/middleware/cors.py", line 83, in call await self.app(scope, receive, send) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 79, in call raise exc File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 68, in call await self.app(scope, receive, sender) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 20, in call raise e File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/fastapi/middleware/asyncexitstack.py", line 17, in call await self.app(scope, receive, send) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/starlette/routing.py", line 718, in call await route.handle(scope, receive, send) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/starlette/routing.py", line 276, in handle await self.app(scope, receive, send) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/starlette/routing.py", line 66, in app response = await func(request) File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/fastapi/routing.py", line 274, in app raw_response = await run_endpoint_function( File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/fastapi/routing.py", line 191, in run_endpoint_function return await dependant.call(**values) File "/workspace/functionary/server_vllm.py", line 398, in create_chat_completion async for res in result_generator: File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/engine/async_llm_engine.py", line 445, in generate raise e File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/engine/async_llm_engine.py", line 439, in generate async for request_output in stream: File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/engine/async_llm_engine.py", line 70, in anext raise result File "uvloop/cbhandles.pyx", line 63, in uvloop.loop.Handle._run File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/engine/async_llm_engine.py", line 37, in _raise_exception_on_finish raise exc File "/root/miniconda3/envs/agent/lib/python3.10/site-packages/vllm/engine/async_llm_engine.py", line 32, in _raise_exception_on_finish raise AsyncEngineDeadError( vllm.engine.async_llm_engine.AsyncEngineDeadError: Task finished unexpectedly. This should never happen! Please open an issue on Github. See stack trace above for the actual cause.`

jeffreymeetkai commented 7 months ago

Hi, can you try again after installing the requirements.txt in this repo?

If it still fails, can you provide more information such as the vllm version you used, the command you used that lead to this error so I can try to reproduce?