An MLX-powered C++ linear programming solver with Metal acceleration on Apple Silicon

Run full Kimi K3 on a single device. And an OpenAI-compatible API server for local chat and coding agents.

Think with AI beyond the chat box. A shared canvas for handwriting, equations, diagrams, and spatial reasoning.

EdgeBench: Unveiling scaling laws of learning from real-world environments

🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

GPU-accelerated Llama3.java inference in pure Java using TornadoVM.

Implement a ChatGPT-like LLM in PyTorch from scratch, step by step

npx ccusage

Agent Reinforcement Trainer: train multi-step agents for real-world tasks using GRPO. Give your agents on-the-job training. Reinforcement learning for Qwen3.6, GPT-OSS, Llama, and more!

AlphaGo Moment for Model Architecture Discovery.

Master programming by recreating your favorite technologies from scratch.

An open-source EDA infrastructure and tools from netlist to GDS

⛽️「算法通关手册」：从零开始的「算法与数据结构」学习教程，200 道「算法面试热门题目」，1000+ 道「LeetCode 题目解析」，持续更新中！

A lightweight, high-performance C++ benchmarking and tracking library for effortless function profiling in both development and production environments. Features single-header integration, minimal …

LLM inference in C/C++

llama3.cuda is a pure C/CUDA implementation for Llama 3 model.

Run GGUF models easily with a KoboldAI UI. One File. Zero Install.

Chat with your documents on your local device using GPT models. No data leaves your device and 100% private.

[ICML 2024] BiLLM: Pushing the Limit of Post-Training Quantization for LLMs

A microbenchmark support library

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

AlwaysReddy is a LLM voice assistant that is always just a hotkey away.

A simple speech-to-text and text-to-speech AI chatbot that can be run fully offline.

Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)

function calling-based LLM agents

🕹 OpenPARF: An Open-Source Placement and Routing Framework for Large-Scale Heterogeneous FPGAs with Deep Learning Toolkit