Skip to content
@triton-inference-server

Triton Inference Server

README.md

NVIDIA Triton Inference Server Organization

NVIDIA Triton Inference Server provides a cloud and edge inferencing solution optimized for both CPUs and GPUs.

This top level GitHub organization host repositories for officially supported backends, including TensorRT, TensorFlow, PyTorch, Python, ONNX Runtime, and OpenVino. The organization also hosts several popular Triton tools, including:

  • Model Analyzer: A tool to analyze the runtime performance of a model and provide an optimized model configuration for Triton Inference Server.

  • Model Navigator: a tool that provides the ability to automate the process of moving a model from source to optimal format and configuration for deployment on Triton Inference Server.

Getting Started

To learn about NVIDIA Triton Inference Server, refer to the Triton developer page and read our Quickstart Guide. Official Triton Docker containers are available from NVIDIA NGC.

Product Documentation

User documentation on Triton features, APIs, and architecture is located in the server documents on GitHub. A table of contents for the user documentation is located in the server README file.

Release Notes, Support Matrix, and Licenses information are available in the NVIDIA Triton Inference Server Documentation.

Examples

Specific end-to-end examples for popular models, such as ResNet, BERT, and DLRM are located in the NVIDIA Deep Learning Examples page on GitHub. Additional generic examples can be found in the server documents.

FAQ

For technical questions about Triton Inference Server, please consult the Triton FAQ Guide. Information about future support & updates for Triton can be found in the Dynamo FAQ Guide.

Feedback

Share feedback or ask questions about NVIDIA Triton Inference Server by filing a GitHub issue.

Pinned Loading

  1. server server Public

    The Triton Inference Server provides an optimized cloud and edge inferencing solution.

    Python 10.4k 1.7k

  2. core core Public

    The core library and APIs implementing the Triton Inference Server.

    C++ 169 132

  3. backend backend Public

    Common source, scripts and utilities for creating Triton backends.

    C++ 368 104

  4. client client Public

    Triton Python, C++ and Java client libraries, and GRPC-generated client examples for go, java and scala.

    Python 681 253

  5. model_analyzer model_analyzer Public

    Triton Model Analyzer is a CLI tool to help with better understanding of the compute and memory requirements of the Triton Inference Server models.

    Python 506 85

  6. model_navigator model_navigator Public

    Triton Model Navigator is an inference toolkit designed for optimizing and deploying Deep Learning models with a focus on NVIDIA GPUs.

    Python 218 28

Repositories

Showing 10 of 36 repositories
  • TensorRT-LLM Public Forked from NVIDIA/TensorRT-LLM

    TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. TensorRT LLM also contains components to create Python and C++ runtimes that orchestrate the inference execution in a performant way.

    triton-inference-server/TensorRT-LLM’s past year of commit activity
    Python 1 2,149 0 0 Updated Feb 27, 2026
  • pytorch_backend Public

    The Triton backend for the PyTorch TorchScript models.

    triton-inference-server/pytorch_backend’s past year of commit activity
    C++ 173 BSD-3-Clause 68 0 9 Updated Feb 26, 2026
  • python_backend Public

    Triton backend that enables pre-process, post-processing and other logic to be implemented in Python.

    triton-inference-server/python_backend’s past year of commit activity
    C++ 672 BSD-3-Clause 195 0 20 Updated Feb 26, 2026
  • server Public

    The Triton Inference Server provides an optimized cloud and edge inferencing solution.

    triton-inference-server/server’s past year of commit activity
    Python 10,389 BSD-3-Clause 1,722 781 (3 issues need help) 96 Updated Feb 26, 2026
  • dali_backend Public

    The Triton backend that allows running GPU-accelerated data pre-processing pipelines implemented in DALI's python API.

    triton-inference-server/dali_backend’s past year of commit activity
    C++ 141 MIT 35 22 (9 issues need help) 6 Updated Feb 26, 2026
  • core Public

    The core library and APIs implementing the Triton Inference Server.

    triton-inference-server/core’s past year of commit activity
    C++ 169 BSD-3-Clause 132 0 28 Updated Feb 26, 2026
  • common Public

    Common source, scripts and utilities shared across all Triton repositories.

    triton-inference-server/common’s past year of commit activity
    C++ 79 BSD-3-Clause 78 0 8 Updated Feb 25, 2026
  • onnxruntime_backend Public

    The Triton backend for the ONNX Runtime.

    triton-inference-server/onnxruntime_backend’s past year of commit activity
    C++ 173 BSD-3-Clause 78 74 7 Updated Feb 25, 2026
  • client Public

    Triton Python, C++ and Java client libraries, and GRPC-generated client examples for go, java and scala.

    triton-inference-server/client’s past year of commit activity
    Python 681 BSD-3-Clause 253 57 34 Updated Feb 25, 2026
  • tensorrtllm_backend Public

    The Triton TensorRT-LLM Backend

    triton-inference-server/tensorrtllm_backend’s past year of commit activity
    926 Apache-2.0 134 318 (1 issue needs help) 25 Updated Feb 21, 2026
View all repositories