Recommended Installation Method#
Triton SDK Container#
The recommended way to “install” Perf Analyzer is to run the pre-built executable from within the Triton SDK docker container available on the NVIDIA GPU Cloud Catalog. As long as the SDK container has its network exposed to the address and port of the inference server, Perf Analyzer will be able to run.
export RELEASE=<yy.mm> # e.g. to use the release from the end of February of 2023, do `export RELEASE=23.02`
docker pull nvcr.io/nvidia/tritonserver:${RELEASE}-py3-sdk
docker run --gpus all --rm -it --net host nvcr.io/nvidia/tritonserver:${RELEASE}-py3-sdk
# inside container
perf_analyzer -m <model>
Alternative Installation Methods#
Pip#
pip install tritonclient
perf_analyzer -m <model>
Warning: If any runtime dependencies are missing, Perf Analyzer will produce errors showing which ones are missing. You will need to manually install them.
Build from Source#
The Triton SDK container is used for building, so some build and runtime dependencies are already installed.
export RELEASE=<yy.mm> # e.g. to use the release from the end of February of 2023, do `export RELEASE=23.02`
docker pull nvcr.io/nvidia/tritonserver:${RELEASE}-py3-sdk
docker run --gpus all --rm -it --net host nvcr.io/nvidia/tritonserver:${RELEASE}-py3-sdk
# inside container
# prep installing newer version of cmake
apt update && apt install -y gpg wget && wget -O - https://apt.kitware.com/keys/kitware-archive-latest.asc 2>/dev/null | gpg --dearmor - | tee /usr/share/keyrings/kitware-archive-keyring.gpg >/dev/null && . /etc/os-release && echo "deb [signed-by=/usr/share/keyrings/kitware-archive-keyring.gpg] https://apt.kitware.com/ubuntu/ $UBUNTU_CODENAME main" | tee /etc/apt/sources.list.d/kitware.list >/dev/null
# install build/runtime dependencies
apt update && apt install -y cmake-data=3.27.7* cmake=3.27.7* libcurl4-openssl-dev rapidjson-dev
rm -rf perf_analyzer ; git clone --depth 1 https://github.com/triton-inference-server/perf_analyzer
mkdir perf_analyzer/build ; cd perf_analyzer/build
cmake ..
make -j8 perf-analyzer
perf_analyzer/src/perf-analyzer-build/perf_analyzer -m <model>
To enable CUDA shared memory, add
-DTRITON_ENABLE_GPU=ON
to thecmake
command.To enable C API mode, add
-DTRITON_ENABLE_PERF_ANALYZER_C_API=ON
to thecmake
command.To enable TorchServe backend, add
-DTRITON_ENABLE_PERF_ANALYZER_TS=ON
to thecmake
command.To enable Tensorflow Serving backend, add
-DTRITON_ENABLE_PERF_ANALYZER_TFS=ON
to thecmake
command.