lmdeploy icon indicating copy to clipboard operation
lmdeploy copied to clipboard
Published 2 months ago • verified publisher icon InternLM

[Bug] 0.10.1版本多模态大模型请求报文中未送任何text提示词时会直接报错。0.10.2版本也未解决。

Open waveman800 opened this issue 2 months ago • 3 comments

Checklist

  • [ ] 1. I have searched related issues but cannot get the expected help.
  • [x] 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

0.10.1版本多模态大模型请求报文中未送任何text提示词时会直接报错，应该兼容下为空仍会送空字符给大模型。

Reproduction

docker run -d --name lmdeploy_Qwen2.5-VL-32B-Instruct
--runtime=nvidia --gpus "device=0"
-v /home/devuser/models/other-models:/root/model
-p 8015:23333
--ipc=host
harbor.bhidi.com/ai/lmdeploy:0.10.1-long-cuda118-fixed1
sh -c "pip install qwen_vl_utils &&
lmdeploy serve api_server /root/model/Qwen2.5-VL-32B-Instruct-AWQ
--model-name Qwen2.5-VL-32B-Instruct-AWQ
--session-len 120000
--cache-max-entry-count 0.8
--max-batch-size 4
--backend turbomind
--enable-dynamic-compression
--importance-threshold 0.6
--min-compression-ratio 0.5
--max-compression-ratio 0.8
--segment-strategy paragraph"

Environment

sys.platform: linux
Python: 3.10.12 (main, Aug 15 2025, 14:32:43) [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
NVCC: Cuda compilation tools, release 11.8, V11.8.89
GCC: x86_64-linux-gnu-gcc (Ubuntu 11.4.0-1ubuntu1~22.04.2) 11.4.0
PyTorch: 2.6.0+cu118
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 11.8
  - 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_37,code=sm_37;-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=11.8, 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+cu118
LMDeploy: 0.10.1+
transformers: 4.56.1
fastapi: 0.121.3
pydantic: 2.12.4
triton: 3.2.0
NVIDIA Topology: 
	GPU0	CPU Affinity	NUMA Affinity	GPU NUMA ID
GPU0	 X 	0-15	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 # NVLinks

Error traceback

ERROR:    Exception in ASGI application

+ Exception Group Traceback (most recent call last):

|   File "/opt/py3/lib/python3.10/site-packages/starlette/_utils.py", line 79, in collapse_excgroups

|     yield

|   File "/opt/py3/lib/python3.10/site-packages/starlette/responses.py", line 270, in __call__

|     async with anyio.create_task_group() as task_group:

|   File "/opt/py3/lib/python3.10/site-packages/anyio/_backends/_asyncio.py", line 781, 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 1134, in __call__

|     await super().__call__(scope, receive, send)

|   File "/opt/py3/lib/python3.10/site-packages/starlette/applications.py", line 107, in __call__

|     await self.middleware_stack(scope, receive, send)

|   File "/opt/py3/lib/python3.10/site-packages/starlette/middleware/errors.py", line 186, in __call__

|     raise exc

|   File "/opt/py3/lib/python3.10/site-packages/starlette/middleware/errors.py", line 164, 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 63, 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/fastapi/middleware/asyncexitstack.py", line 18, in __call__

|     await self.app(scope, receive, send)

|   File "/opt/py3/lib/python3.10/site-packages/starlette/routing.py", line 716, in __call__

|     await self.middleware_stack(scope, receive, send)

|   File "/opt/py3/lib/python3.10/site-packages/starlette/routing.py", line 736, in app

|     await route.handle(scope, receive, send)

|   File "/opt/py3/lib/python3.10/site-packages/starlette/routing.py", line 290, in handle

|     await self.app(scope, receive, send)

|   File "/opt/py3/lib/python3.10/site-packages/fastapi/routing.py", line 125, 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/fastapi/routing.py", line 112, in app

|     await response(scope, receive, send)

|   File "/opt/py3/lib/python3.10/site-packages/starlette/responses.py", line 269, 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 85, in collapse_excgroups

|     raise exc

|   File "/opt/py3/lib/python3.10/site-packages/starlette/responses.py", line 273, in wrap

|     await func()

|   File "/opt/py3/lib/python3.10/site-packages/starlette/responses.py", line 253, in stream_response

|     async for chunk in self.body_iterator:

|   File "/opt/py3/lib/python3.10/site-packages/lmdeploy/serve/openai/api_server.py", line 489, in completion_stream_generator

|     async for res in result_generator:

|   File "/opt/py3/lib/python3.10/site-packages/lmdeploy/serve/async_engine.py", line 765, in generate

|     prompt_input = await self._get_prompt_input(prompt,

|   File "/opt/py3/lib/python3.10/site-packages/lmdeploy/serve/vl_async_engine.py", line 99, in _get_prompt_input

|     results = await self.vl_encoder.wrap_for_turbomind(results,

|   File "/opt/py3/lib/python3.10/site-packages/lmdeploy/vl/engine.py", line 124, in wrap_for_turbomind

|     result = self.model.to_turbomind(messages,

|   File "/opt/py3/lib/python3.10/site-packages/lmdeploy/vl/model/qwen2.py", line 186, in to_turbomind

|     prompt, IMAGE_TOKEN = self.proc_messages(messages, chat_template, sequence_start)

|   File "/opt/py3/lib/python3.10/site-packages/lmdeploy/vl/model/qwen2.py", line 140, in proc_messages

|     prompt = content[0]

| IndexError: list index out of range

waveman800 avatar Nov 23 '25 01:11 waveman800

我也遇到了这个问题，只发图片会报错，在qwen2.5-vl-72b-instruct-awq上

mokieli avatar Nov 23 '25 12:11 mokieli

我已经自己解决了，兼容下文本空值就好了 ---- 回复的原邮件 ---- 发件人 @.> 日期 2025年11月23日 20:38 收件人 @.> 抄送至 @.>@.> 主题 Re: [InternLM/lmdeploy] [Bug] 0.10.1版本多模态大模型请求报文中未送任何text提示词时会直接报错。0.10.2版本也未解决。 (Issue #4145) mokieli left a comment (InternLM/lmdeploy#4145) 我也遇到了这个问题，只发图片会报错，在qwen2.5-vl-72b-instruct-awq上 — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: @.***>

waveman800 avatar Nov 23 '25 12:11 waveman800

https://github.com/InternLM/lmdeploy/pull/4141 is addressing this issue

lvhan028 avatar Nov 24 '25 04:11 lvhan028