increase the GPU utilization rate, even when the parameter "--cache-max-entry-count" is set to 0.99 #3359
Description
The GPU utilizaiton rate can only reach to about 75%
This is how I startup
lmdeploy serve api_server /data/models/deepseek-vl2 --tp 4 --server-port 8001 --dtype
float16 --log-level INFO --backend pytorch --max-batch-size 64 --cache-max-entry-count 0.99 --session-len 32768 --eager-mode --quant-policy 8
when i ran the benchmark test ,I want to reduce the TTFT : python3 profile_restful_api.py --backend lmdeploy --model /data/models/deepseek-vl2 --dataset-path /data/training_data/ShareGPT_V3_unfiltered_cleaned_split.json --dataset-name random --random-input-len 2048 --random-output-len 200 --num-prompts 5 --random-range-ratio 1
but first ,I need to utilize the GPU more .
Here is the lmdeploy check_env:
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 0,1,2,3: Tesla V100S-PCIE-32GB
CUDA_HOME: /usr/local/cuda-12.2
NVCC: Cuda compilation tools, release 12.2, V12.2.91
GCC: gcc (GCC) 8.3.1 20190311 (Red Hat 8.3.1-3)
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: 0.7.1+
transformers: 4.47.0
gradio: Not Found
fastapi: 0.115.11
pydantic: 2.10.6
triton: 3.1.0
NVIDIA Topology:
GPU0 GPU1 GPU2 GPU3 CPU Affinity NUMA Affinity GPU NUMA ID
GPU0 X PHB PHB PHB 0-31 0-1 N/A
GPU1 PHB X PHB PHB 0-31 0-1 N/A
GPU2 PHB PHB X PHB 0-31 0-1 N/A
GPU3 PHB PHB PHB X 0-31 0-1 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