A fast serialization and validation library, with builtin support for JSON, MessagePack, YAML, and TOML

A high-throughput and memory-efficient inference and serving engine for LLMs

VS Code in the browser

The Triton TensorRT-LLM Backend

Helper scripts to install pip, in a Python installation that doesn't have it.

GFPGAN aims at developing Practical Algorithms for Real-world Face Restoration.

Runs tests multiple times to expose flakiness.

HTTP load generator, ApacheBench (ab) replacement

An alternative plugin for pytest to make it support async tests and fixtures

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

Provides end-to-end model development pipelines for LLMs and Multimodal models that can be launched on-prem or cloud-native.

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