Recommended Installation Method#

Triton SDK Container#

The recommended way to access 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 December of 2024, do `export RELEASE=24.12`

docker run --rm --gpus=all -it --net=host nvcr.io/nvidia/tritonserver:${RELEASE}-py3-sdk

# inside container
perf_analyzer -m <model>

Alternative Installation Methods#

pip
Build from Source

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#

docker run --rm --gpus=all -it --net=host ubuntu:24.04

# inside container, install build/runtime dependencies
apt update && DEBIAN_FRONTEND=noninteractive apt install -y cmake g++ git libssl-dev nvidia-cuda-toolkit python3 rapidjson-dev zlib1g-dev

git clone --depth=1 https://github.com/triton-inference-server/perf_analyzer.git

mkdir perf_analyzer/build

cmake -B perf_analyzer/build -S perf_analyzer

cmake --build perf_analyzer/build -- -j8

export PATH=$(pwd)/perf_analyzer/build/perf_analyzer/src/perf-analyzer-build:$PATH

perf_analyzer -m <model>

To enable OpenAI mode, add -D TRITON_ENABLE_PERF_ANALYZER_OPENAI=ON to the first cmake command.
To enable C API mode, add -D TRITON_ENABLE_PERF_ANALYZER_C_API=ON to the first cmake command.
To enable TorchServe backend, add -D TRITON_ENABLE_PERF_ANALYZER_TS=ON to the first cmake command.
To enable Tensorflow Serving backend, add -D TRITON_ENABLE_PERF_ANALYZER_TFS=ON to the first cmake command.
To disable CUDA shared memory support and the dependency on CUDA toolkit libraries, add -D TRITON_ENABLE_GPU=OFF to the first cmake command.