FlashInfer: Kernel Library for LLM Serving

Efficient, Flexible and Portable Structured Generation

Official NetHack Git Repository

NVIDIA Linux open GPU kernel module source

SGLang is a fast serving framework for large language models and vision language models.

Development repository for the Triton language and compiler

CUDA Templates for Linear Algebra Subroutines

A multi-level tensor algebra superoptimizer

Source Code of GNU TeXmacs, Developers Guide ==>

MLX: An array framework for Apple silicon

Source code to pbrt, the ray tracer described in the forthcoming 4th edition of the "Physically Based Rendering: From Theory to Implementation" book.

Apple GPU microarchitecture

Optimized primitives for collective multi-GPU communication

Project website of FlashInfer project

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

Serving multiple LoRA finetuned LLM as one

Enable everyone to develop, optimize and deploy AI models natively on everyone's devices.

The UW SAMPL group's website.

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

Bringing large-language models and chat to web browsers. Everything runs inside the browser with no server support.

A home for the final text of all TVM RFCs.

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models

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