FlashInfer: Kernel Library for LLM Serving

Official inference library for Mistral models

An extremely fast Python linter and code formatter, written in Rust.

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

A library to analyze PyTorch traces.

Super-Efficient RLHF Training of LLMs with Parameter Reallocation

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch and FLAX.

Simple and efficient pytorch-native transformer text generation in <1000 LOC of python.

Taming Transformers for High-Resolution Image Synthesis

Official Jax Implementation of MaskGIT

Pandora: Towards General World Model with Natural Language Actions and Video States

Profiling and inspecting memory in pytorch

LLM training in simple, raw C/CUDA

Easy Parallel Library (EPL) is a general and efficient deep learning framework for distributed model training.

An application-focused API for memory management on NUMA & GPU architectures

Grok open release

Task-based datasets, preprocessing, and evaluation for sequence models.

An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).

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

A fast implementation of T5/UL2 in PyTorch using Flash Attention

Building a quick conversation-based search demo with Lepton AI.

Open standard for machine learning interoperability

TensorRT-LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and build TensorRT engines that contain state-of-the-art optimizations to perform inference efficie…

StreamDiffusion: A Pipeline-Level Solution for Real-Time Interactive Generation

Mamba SSM architecture