An advanced Twitter scraping & OSINT tool written in Python that doesn't use Twitter's API, allowing you to scrape a user's followers, following, Tweets and more while evading most API limitations.

Bitcoin Core integration/staging tree

A personal news aggregator to pull information from multi-sources + LLM (ChatGPT/Gemini/Ollama via LangChain) to help us reading efficiently with less noises, the sources including: Tweets, RSS, Yo…

文颜 MCP Server 可以让 AI 自动将 Markdown 文章排版后发布至微信公众号。

Supercharge Your LLM with the Fastest KV Cache Layer

Student version of Assignment 1 for Stanford CS336 - Language Modeling From Scratch

Profiling and inspecting memory in pytorch

Implementation for FP8/INT8 Rollout for RL training without performence drop.

A curated list of papers, theses, datasets, and tools related to the application of Machine Learning for Software Engineering

Collection of awesome LLM apps with AI Agents and RAG using OpenAI, Anthropic, Gemini and opensource models.

自学入门Web3不是一件容易的事，作为一个刚刚入门Web3的新人，梳理一下最简单直观的Web3小白入门教程。整合开源社区优质资源，为大家从入门到精通web3指路。每周更新

LLM model quantization (compression) toolkit with hw acceleration support for Nvidia CUDA, AMD ROCm, Intel XPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

🐉 Making Rust a first-class language and ecosystem for GPU shaders 🚧

Demo project showing a single Rust codebase running on CPU and directly on GPUs

Official implementation of Half-Quadratic Quantization (HQQ)

An easy-to-use LLMs quantization package with user-friendly apis, based on GPTQ algorithm.

Collect libraries and packages about blockchain/cryptography in Rust

Efficient Triton Kernels for LLM Training

An open-source AI agent that brings the power of Gemini directly into your terminal.

Fast low-bit matmul kernels in Triton

verl: Volcano Engine Reinforcement Learning for LLMs

Nano vLLM

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

oneAPI Deep Neural Network Library (oneDNN)

Distributed Compiler based on Triton for Parallel Systems

Puzzles for learning Triton

FlagGems is an operator library for large language models implemented in the Triton Language.