[Bug] 0.10.1版本调用工具时会出现content异常的报错。 #4134
Description
Checklist
- 1. I have searched related issues but cannot get the expected help.
- 2. The bug has not been fixed in the latest version.
- 3. Please note that if the bug-related issue you submitted lacks corresponding environment info and a minimal reproducible demo, it will be challenging for us to reproduce and resolve the issue, reducing the likelihood of receiving feedback.
Describe the bug
在调用工具的时候，会出现content异常的问题，大模型是Qwen3-14B-AWQ。
具体日志见下：INFO: 10.216.7.14:50394 - "POST /v1/chat/completions HTTP/1.1" 200 OK
ERROR: Exception in ASGI application
- Exception Group Traceback (most recent call last):
| File "/opt/py3/lib/python3.10/site-packages/starlette/_utils.py", line 76, in collapse_excgroups
| yield
| File "/opt/py3/lib/python3.10/site-packages/starlette/responses.py", line 263, in call
| async with anyio.create_task_group() as task_group:
| File "/opt/py3/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 772, in aexit
| raise BaseExceptionGroup(
| exceptiongroup.ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
+-+---------------- 1 ----------------
| Traceback (most recent call last):
| File "/opt/py3/lib/python3.10/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi
| result = await app( # type: ignore[func-returns-value]
| File "/opt/py3/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in call
| return await self.app(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/fastapi/applications.py", line 1054, in call
| await super().call(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/applications.py", line 112, in call
| await self.middleware_stack(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/middleware/errors.py", line 187, in call
| raise exc
| File "/opt/py3/lib/python3.10/site-packages/starlette/middleware/errors.py", line 165, in call
| await self.app(scope, receive, _send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/middleware/cors.py", line 85, in call
| await self.app(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 62, in call
| await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
| raise exc
| File "/opt/py3/lib/python3.10/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
| await app(scope, receive, sender)
| File "/opt/py3/lib/python3.10/site-packages/starlette/routing.py", line 714, in call
| await self.middleware_stack(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/routing.py", line 734, in app
| await route.handle(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/routing.py", line 288, in handle
| await self.app(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/routing.py", line 76, in app
| await wrap_app_handling_exceptions(app, request)(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
| raise exc
| File "/opt/py3/lib/python3.10/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
| await app(scope, receive, sender)
| File "/opt/py3/lib/python3.10/site-packages/starlette/routing.py", line 74, in app
| await response(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/responses.py", line 262, in call
| with collapse_excgroups():
| File "/usr/lib/python3.10/contextlib.py", line 153, in exit
| self.gen.throw(typ, value, traceback)
| File "/opt/py3/lib/python3.10/site-packages/starlette/_utils.py", line 82, in collapse_excgroups
| raise exc
| File "/opt/py3/lib/python3.10/site-packages/starlette/responses.py", line 266, in wrap
| await func()
| File "/opt/py3/lib/python3.10/site-packages/starlette/responses.py", line 246, in stream_response
| async for chunk in self.body_iterator:
| File "/opt/lmdeploy/lmdeploy/serve/openai/api_server.py", line 459, in completion_stream_generator
| async for res in result_generator:
| File "/opt/lmdeploy/lmdeploy/serve/async_engine.py", line 728, in generate
| prompt_input = await self._get_prompt_input(prompt,
| File "/opt/lmdeploy/lmdeploy/serve/async_engine.py", line 608, in _get_prompt_input
| prompt = chat_template.messages2prompt(messages, sequence_start, tools=tools)
| File "/opt/lmdeploy/lmdeploy/model.py", line 229, in messages2prompt
| content = get_text(message['content'])
| KeyError: 'content'
+------------------------------------
During handling of the above exception, another exception occurred:
Reproduction
docker run -d --name lmdeploy_Qwen3-14B-AWQ
--runtime=nvidia --gpus "device=1"
-v /mnt/nvme0/models:/root/model
-v /mnt/nvme0/logs:/root/logs
-p 8010:23333
--ipc=host
harbor.bhidi.com/ai/lmdeploy:0.10.1-long-cuda118
lmdeploy serve api_server /root/model/Qwen3-14B-AWQ
--model-name Qwen3-14B-AWQ --session-len 262144
--cache-max-entry-count 0.8 --max-batch-size 20
--backend turbomind --model-format awq
--tool-call-parser qwen
--enable-dynamic-compression
--importance-threshold 0.6
--min-compression-ratio 0.5
--max-compression-ratio 0.8
--segment-strategy paragraph
以上脚本执行的镜像是我在0.10.1版本上做了二次开发的打包镜像。
Environment
sys.platform: linux
Python: 3.10.12 (main, Feb 4 2025, 14:57:36) [GCC 11.4.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0: NVIDIA GeForce RTX 4090
CUDA_HOME: /usr/local/cuda-12.1
NVCC: Cuda compilation tools, release 12.1, V12.1.105
GCC: x86_64-linux-gnu-gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
PyTorch: 2.6.0+cu124
PyTorch compiling details: PyTorch built with:
- GCC 9.3
- C++ Version: 201703
- Intel(R) oneAPI Math Kernel Library Version 2024.2-Product Build 20240605 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v3.5.3 (Git Hash 66f0cb9eb66affd2da3bf5f8d897376f04aae6af)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- LAPACK is enabled (usually provided by MKL)
- NNPACK is enabled
- CPU capability usage: AVX512
- CUDA Runtime 12.4
- NVCC architecture flags: -gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_90,code=sm_90
- CuDNN 90.1
- Magma 2.6.1
- Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, COMMIT_SHA=2236df1770800ffea5697b11b0bb0d910b2e59e1, CUDA_VERSION=12.4, CUDNN_VERSION=9.1.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DLIBKINETO_NOXPUPTI=ON -DUSE_FBGEMM -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, TORCH_VERSION=2.6.0, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF,
TorchVision: 0.21.0+cu124
LMDeploy: 0.8.0+68eca6e
transformers: 4.52.4
gradio: 3.43.0
fastapi: 0.115.12
pydantic: 2.11.7
triton: 3.2.0
NVIDIA Topology:
GPU0 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X 0-31,64-95 0 N/A
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 # NVLinksError traceback
INFO: 10.216.7.14:50394 - "POST /v1/chat/completions HTTP/1.1" 200 OK
ERROR: Exception in ASGI application
+ Exception Group Traceback (most recent call last):
| File "/opt/py3/lib/python3.10/site-packages/starlette/_utils.py", line 76, in collapse_excgroups
| yield
| File "/opt/py3/lib/python3.10/site-packages/starlette/responses.py", line 263, in __call__
| async with anyio.create_task_group() as task_group:
| File "/opt/py3/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 772, in __aexit__
| raise BaseExceptionGroup(
| exceptiongroup.ExceptionGroup: unhandled errors in a TaskGroup (1 sub-exception)
+-+---------------- 1 ----------------
| Traceback (most recent call last):
| File "/opt/py3/lib/python3.10/site-packages/uvicorn/protocols/http/h11_impl.py", line 403, in run_asgi
| result = await app( # type: ignore[func-returns-value]
| File "/opt/py3/lib/python3.10/site-packages/uvicorn/middleware/proxy_headers.py", line 60, in __call__
| return await self.app(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/fastapi/applications.py", line 1054, in __call__
| await super().__call__(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/applications.py", line 112, in __call__
| await self.middleware_stack(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/middleware/errors.py", line 187, in __call__
| raise exc
| File "/opt/py3/lib/python3.10/site-packages/starlette/middleware/errors.py", line 165, in __call__
| await self.app(scope, receive, _send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/middleware/cors.py", line 85, in __call__
| await self.app(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/middleware/exceptions.py", line 62, in __call__
| await wrap_app_handling_exceptions(self.app, conn)(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
| raise exc
| File "/opt/py3/lib/python3.10/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
| await app(scope, receive, sender)
| File "/opt/py3/lib/python3.10/site-packages/starlette/routing.py", line 714, in __call__
| await self.middleware_stack(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/routing.py", line 734, in app
| await route.handle(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/routing.py", line 288, in handle
| await self.app(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/routing.py", line 76, in app
| await wrap_app_handling_exceptions(app, request)(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/_exception_handler.py", line 53, in wrapped_app
| raise exc
| File "/opt/py3/lib/python3.10/site-packages/starlette/_exception_handler.py", line 42, in wrapped_app
| await app(scope, receive, sender)
| File "/opt/py3/lib/python3.10/site-packages/starlette/routing.py", line 74, in app
| await response(scope, receive, send)
| File "/opt/py3/lib/python3.10/site-packages/starlette/responses.py", line 262, in __call__
| with collapse_excgroups():
| File "/usr/lib/python3.10/contextlib.py", line 153, in __exit__
| self.gen.throw(typ, value, traceback)
| File "/opt/py3/lib/python3.10/site-packages/starlette/_utils.py", line 82, in collapse_excgroups
| raise exc
| File "/opt/py3/lib/python3.10/site-packages/starlette/responses.py", line 266, in wrap
| await func()
| File "/opt/py3/lib/python3.10/site-packages/starlette/responses.py", line 246, in stream_response
| async for chunk in self.body_iterator:
| File "/opt/lmdeploy/lmdeploy/serve/openai/api_server.py", line 459, in completion_stream_generator
| async for res in result_generator:
| File "/opt/lmdeploy/lmdeploy/serve/async_engine.py", line 728, in generate
| prompt_input = await self._get_prompt_input(prompt,
| File "/opt/lmdeploy/lmdeploy/serve/async_engine.py", line 608, in _get_prompt_input
| prompt = chat_template.messages2prompt(messages, sequence_start, tools=tools)
| File "/opt/lmdeploy/lmdeploy/model.py", line 229, in messages2prompt
| content = get_text(message['content'])
| KeyError: 'content'
+------------------------------------
During handling of the above exception, another exception occurred: