Empowering everyone to build reliable and efficient software.

The official Python library for the OpenAI API

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

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

TensorRT Model Optimizer is a unified library of state-of-the-art model optimization techniques such as quantization and sparsity. It compresses deep learning models for downstream deployment frame…

Generative Models by Stability AI

High-Resolution Image Synthesis with Latent Diffusion Models

Open deep learning compiler stack for cpu, gpu and specialized accelerators

Serving multiple LoRA finetuned LLM as one

Universal LLM Deployment Engine with ML Compilation

High-performance In-browser LLM Inference Engine

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

Bringing stable diffusion models to web browsers. Everything runs inside the browser with no server support.

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

Development repository for the Triton language and compiler

A home for the final text of all TVM RFCs.

Temp repo for prototyping relax(relay next), the effort will be upstreamed. We use the wiki pages on this repo to host design docs.

Object detection, 3D detection, and pose estimation using center point detection:

A retargetable MLIR-based machine learning compiler and runtime toolkit.

A performant and modular runtime for TensorFlow

Code for the paper "Evolution Strategies as a Scalable Alternative to Reinforcement Learning"

Serve, optimize and scale PyTorch models in production

YoloV3 Implemented in Tensorflow 2.0

[ICLR 2019] ProxylessNAS: Direct Neural Architecture Search on Target Task and Hardware

a language for fast, portable data-parallel computation

A Python framework for creating, editing, and invoking Noisy Intermediate Scale Quantum (NISQ) circuits.

ncnn is a high-performance neural network inference framework optimized for the mobile platform