Open ABI and FFI for Machine Learning Systems

A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.

A community-maintained Python framework for creating mathematical animations.

Unofficial description of the CUDA assembly (SASS) instruction sets.

Assembler and Decompiler for NVIDIA (Maxwell Pascal Volta Turing Ampere) GPUs.

Third party assembler and GEMM library for NVIDIA Kepler GPU

Nvidia Instruction Set Specification Generator

Helpful kernel tutorials and examples for tile-based GPU programming

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

Collective communications library with various primitives for multi-machine training.

🎯 告别信息过载，AI 助你看懂新闻资讯热点，简单的舆情监控分析 - 多平台热点聚合+基于 MCP 的AI分析工具。监控35个平台（抖音、知乎、B站、华尔街见闻、财联社等），智能筛选+自动推送+AI对话分析（用自然语言深度挖掘新闻：趋势追踪、情感分析、相似检索等13种工具）。支持企业微信/个人微信/飞书/钉钉/Telegram/邮件/ntfy/bark/slack 推送，1分钟手机通知，无需…

cuVS - a library for vector search and clustering on the GPU

Efficient Triton Kernels for LLM Training

An unofficial cuda assembler, for all generations of SASS, hopefully ：）

🍒 Cherry Studio is a desktop client that supports for multiple LLM providers.

Optimized primitives for collective multi-GPU communication

Fast and memory-efficient exact attention

The Modular Platform (includes MAX & Mojo)

DeepEP: an efficient expert-parallel communication library

collection of benchmarks to measure basic GPU capabilities

A Quirky Assortment of CuTe Kernels

A markup-based typesetting system that is powerful and easy to learn.

ASCIIFlow

LMDeploy is a toolkit for compressing, deploying, and serving LLMs.

Low-bit LLM inference on CPU/NPU with lookup table

FlashInfer: Kernel Library for LLM Serving

Efficient Top-K implementation on the GPU

A collection of my personal dotfiles