Stars
TokenSpeed is a speed-of-light LLM inference engine.
GPU & Accelerator process monitoring for AMD, Apple, Huawei, Intel, NVIDIA and Qualcomm
Secure and fast microVMs for serverless computing.
Skills for Real Engineers. Straight from my .agents directory.
The agent that grows with you
Open Multi-Agent Interactive Classroom — Get an immersive, multi-agent learning experience in just one click
AI agents running research on single-GPU nanochat training automatically
Google Workspace CLI — one command-line tool for Drive, Gmail, Calendar, Sheets, Docs, Chat, Admin, and more. Dynamically built from Google Discovery Service. Includes AI agent skills.
A request monitoring system for Claude Code that captures and visualizes all API requests and responses in real time. Helps developers monitor their Context for reviewing and debugging during Vibe …
Browser automation CLI for AI agents
Persistent file-based planning for AI coding agents and long-running tasks. Crash-proof markdown plans, session recovery after /clear and compaction, per-turn re-injection against context rot, dete…
A Flexible Framework for Experiencing Heterogeneous LLM Inference/Fine-tune Optimizations
Minimalistic 4D-parallelism distributed training framework for education purpose
收集所有区块链(BlockChain)技术开发相关资料，包括Fabric和Ethereum开发资料
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
A fast communication-overlapping library for tensor/expert parallelism on GPUs.
Must read research papers and links to tools and datasets that are related to using machine learning for compilers and systems optimisation
A fast GPU memory copy library based on NVIDIA GPUDirect RDMA technology
Running large language models on a single GPU for throughput-oriented scenarios.
C++ standard library reference
Probably the fastest coroutine lib in the world!
CodeQL: the libraries and queries that power security researchers around the world, as well as code scanning in GitHub Advanced Security
Confidential AI deployment with secure enclaves 🔒
The LLVM Project is a collection of modular and reusable compiler and toolchain technologies.
Never ever ever use pixelation as a redaction technique
The Triton Inference Server provides an optimized cloud and edge inferencing solution.