InternLM / InternLM/lmdeploy

[Bug] 在A100 40GB上使用profile_restful_api.py进行32B AWQ模型长文本基准测试出现bug

Open
#3,331 0 comments 0 reactions 1 assignee Claimed by @AllentDan View on GitHub
Dominant language
Python
Stars
8.1k
Forks
748
Avg merge
6d 2h
Merged PRs (30d)
54

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NVIDIA A100-SXM4-40GB上使用Qwen2.5-32B-Instruct-AWQ模型运行80K profile_restful_api.py测试时出现以下bug。出现这个问题是什么原因呢?麻烦各位大佬解答,万分感谢Orz
server侧的报错:
![Image](https://github.com/user-attachments/assets/105f470d-cca0-417b-a84e-7bdc481f274a)

![Image](https://github.com/user-attachments/assets/311a71c4-2894-4cc4-adbb-4102ab4757b0)

client侧的报错
![Image](https://github.com/user-attachments/assets/9ae29f20-e651-4b38-ac06-6366a17e11b0)

### Reproduction

server.sh
```
lmdeploy serve api_server /data/llm/Qwen2.5-32B-Instruct-AWQ \
--backend pytorch \
--device cuda \
--eager-mode \
--cache-max-entry-count=0.9 \
--enable-prefix-caching \
--session-len 90000 \
--dtype float16
```
client.sh
```
python profile_restful_api.py \
--dataset-path /data/ds/ShareGPT_Vicuna_unfiltered/ShareGPT_V3_unfiltered_cleaned_split.json \
--backend lmdeploy \
--model /data/llm/Qwen2.5-32B-Instruct-AWQ \
--dataset-name random \
--random-input-len 81920 \
--random-output-len 150 \
--num-prompts 2 \
--random-range-ratio 1
```

### Environment

```Shell
sys.platform: linux
Python: 3.10.16 (main, Dec 11 2024, 16:24:50) [GCC 11.2.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0: NVIDIA A100-SXM4-40GB
CUDA_HOME: /usr
NVCC: Cuda compilation tools, release 11.5, V11.5.119
GCC: gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
PyTorch: 2.5.1+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, 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=2.5.1, 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: 0.20.1+cu124
LMDeploy: 0.7.2+1e77ed2
transformers: 4.49.0
gradio: Not Found
fastapi: 0.115.11
pydantic: 2.10.6
triton: 3.1.0
NVIDIA Topology:
GPU0 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X 0-31 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

```Shell
Traceback (most recent call last):
File "/home/cya/lmdeploy/benchmark/profile_restful_api.py", line 1045, in
run_benchmark(args)
File "/home/cya/lmdeploy/benchmark/profile_restful_api.py", line 884, in run_benchmark
return asyncio.run(
File "/home/cya/.conda/envs/lmdeploy_original/lib/python3.10/asyncio/runners.py", line 44, in run
return loop.run_until_complete(main)
File "/home/cya/.conda/envs/lmdeploy_original/lib/python3.10/asyncio/base_events.py", line 649, in run_until_complete
return future.result()
File "/home/cya/lmdeploy/benchmark/profile_restful_api.py", line 629, in benchmark
raise ValueError('Initial test run failed - Please make sure benchmark arguments '
ValueError: Initial test run failed - Please make sure benchmark arguments are correctly specified. Error: Traceback (most recent call last):
File "/home/cya/.conda/envs/lmdeploy_original/lib/python3.10/site-packages/aiohttp/client_proto.py", line 93, in connection_lost
uncompleted = self._parser.feed_eof()
File "aiohttp/_http_parser.pyx", line 508, in aiohttp._http_parser.HttpParser.feed_eof
aiohttp.http_exceptions.TransferEncodingError: 400, message:
Not enough data for satisfy transfer length header.

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

Traceback (most recent call last):
File "/home/cya/lmdeploy/benchmark/profile_restful_api.py", line 168, in async_request_openai_completions
async for chunk_bytes in response.content:
File "/home/cya/.conda/envs/lmdeploy_original/lib/python3.10/site-packages/aiohttp/streams.py", line 52, in __anext__
rv = await self.read_func()
File "/home/cya/.conda/envs/lmdeploy_original/lib/python3.10/site-packages/aiohttp/streams.py", line 352, in readline
return await self.readuntil()
File "/home/cya/.conda/envs/lmdeploy_original/lib/python3.10/site-packages/aiohttp/streams.py", line 386, in readuntil
await self._wait("readuntil")
File "/home/cya/.conda/envs/lmdeploy_original/lib/python3.10/site-packages/aiohttp/streams.py", line 347, in _wait
await waiter
aiohttp.client_exceptions.ClientPayloadError: Response payload is not completed:
```

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.