Triton Inference Server

server

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

pytriton

PyTriton is a Flask/FastAPI-like interface that simplifies Triton's deployment in Python environments.

tensorrtllm_backend

The Triton TensorRT-LLM Backend

client

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

python_backend

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

tutorials

This repository contains tutorials and examples for Triton Inference Server

model_analyzer

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

backend

Common source, scripts and utilities for creating Triton backends.

model_navigator

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

vllm_backend

dali_backend

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

onnxruntime_backend

The Triton backend for the ONNX Runtime.

pytorch_backend

The Triton backend for the PyTorch TorchScript models.

core

The core library and APIs implementing the Triton Inference Server.

fil_backend

FIL backend for the Triton Inference Server

common

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

tensorrt_backend

The Triton backend for TensorRT.

tensorflow_backend

The Triton backend for TensorFlow.

openvino_backend

OpenVINO backend for Triton.

triton_cli

Triton CLI is an open source command line interface that enables users to create, deploy, and profile models served by the Triton Inference Server.

developer_tools

stateful_backend

Triton backend for managing the model state tensors automatically in sequence batcher

contrib

Community contributions to Triton that are not officially supported or maintained by the Triton project.

checksum_repository_agent

The Triton repository agent that verifies model checksums.

redis_cache

TRITONCACHE implementation of a Redis cache

third_party

Third-party source packages that are modified for use in Triton.

identity_backend

Example Triton backend that demonstrates most of the Triton Backend API.

repeat_backend

An example Triton backend that demonstrates sending zero, one, or multiple responses for each request.

local_cache

Implementation of a local in-memory cache for Triton Inference Server's TRITONCACHE API

square_backend

Simple Triton backend used for testing.