在2080ti上四卡推理qwen2-72b-instruct-awq模型非常缓慢

bltcn commented 1 month ago

Checklist

[X] 1. I have searched related issues but cannot get the expected help.
[X] 2. The bug has not been fixed in the latest version.
[X] 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

使用benchmark/profile_restful_api.py进行测试，速度非常缓慢

Reproduction

cd /opt/lmdeploy/benchmark ; /usr/bin/env /opt/pyroot@11433bdefe94:/opt/lmdeploy/benchmark# cd /opt/lmdeploroot/.vscode-server/extensions/ms-python.debugpy-2024.8.0-linux-x64/bundled/libs/debugpy/adapter/../../debugpy/launcher 44565 -- /opt/lmdeploy/benchmark/profile_restful_api.py http://127.0.0.1:23333 Qwen/Qwen2-72B-Instruct-AWQ ./ShareGPT_V3_unfiltered_cleaned_split.json

batch,num_prompts,RPS,RPM,FTL(ave)(s),FTL(min)(s),FTL(max)(s),throughput(out tok/s),throughput(total tok/s) 128,10,0.009,0.533,-,-,-,2.287,5.186

Environment

sys.platform: linux
Python: 3.8.10 (default, Mar 25 2024, 10:42:49) [GCC 9.4.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0,1,2,3,4,5,6,7,8,9: NVIDIA GeForce RTX 2080 Ti
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 11.8, V11.8.89
GCC: x86_64-linux-gnu-gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0
PyTorch: 2.1.0+cu118
PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201703
  - Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v3.1.1 (Git Hash 64f6bcbcbab628e96f33a62c3e975f8535a7bde4)
  - 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 8.7
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, CUDNN_VERSION=8.7.0, 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 -DUSE_FBGEMM -DUSE_QNNPACK -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-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-invalid-partial-specialization -Wno-unused-private-field -Wno-aligned-allocation-unavailable -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.1.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 

TorchVision: 0.16.0+cu118
LMDeploy: 0.5.2.post1+ddb462b
transformers: 4.42.4
gradio: 4.38.1
fastapi: 0.111.1
pydantic: 2.8.2
triton: 2.1.0
NVIDIA Topology: 
        GPU0    GPU1    GPU2    GPU3    GPU4    GPU5    GPU6    GPU7    GPU8    GPU9    CPU Affinity    NUMA Affinity   GPU NUMA ID
GPU0     X      PIX     PIX     PIX     PIX     NODE    NODE    NODE    NODE    NV2     0-19,40-59      0               N/A
GPU1    PIX      X      PIX     NV2     PIX     NODE    NODE    NODE    NODE    SYS     0-19,40-59      0               N/A
GPU2    PIX     PIX      X      PIX     NV2     NODE    NODE    NODE    NODE    SYS     0-19,40-59      0               N/A
GPU3    PIX     NV2     PIX      X      PIX     NODE    NODE    NODE    NODE    SYS     0-19,40-59      0               N/A
GPU4    PIX     PIX     NV2     PIX      X      NODE    NODE    NODE    NODE    SYS     0-19,40-59      0               N/A
GPU5    NODE    NODE    NODE    NODE    NODE     X      NV2     PIX     PIX     SYS     0-19,40-59      0               N/A
GPU6    NODE    NODE    NODE    NODE    NODE    NV2      X      PIX     PIX     SYS     0-19,40-59      0               N/A
GPU7    NODE    NODE    NODE    NODE    NODE    PIX     PIX      X      NV2     SYS     0-19,40-59      0               N/A
GPU8    NODE    NODE    NODE    NODE    NODE    PIX     PIX     NV2      X      SYS     0-19,40-59      0               N/A
GPU9    NV2     SYS     SYS     SYS     SYS     SYS     SYS     SYS     SYS      X      20-39,60-79     1               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

No response

lvhan028 commented 1 month ago

profile_restful_api.py 中默认 num_prompts 是 5000，不知道为何，你这边的结果，显示的是10 4卡2080ti，qwen2-72b-4bits模型，还是不要期待太多了 😂

lzhangzz commented 1 month ago

这拓扑有点奇怪，每张卡分了多少 PCIe lane？

bltcn commented 1 month ago

profile_restful_api.py 中默认 num_prompts 是 5000，不知道为何，你这边的结果，显示的是10 4卡2080ti，qwen2-72b-4bits模型，还是不要期待太多了 😂

因为我修改了源码，否则5000直接超时了

bltcn commented 1 month ago

0.5.3版本解决此问题

InternLM / lmdeploy