Stars
SWE-Marathon: an ultra long-horizon SWE benchmark
Framework for evaluating and improving agents
TokenSpeed is a speed-of-light LLM inference engine.
CL-bench: A Benchmark for Context Learning
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
Scalable toolkit for efficient model reinforcement
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
An Open-source RL System from ByteDance Seed and Tsinghua AIR
A feature-rich command-line audio/video downloader
My learning notes for ML SYS.
The context API to search, scrape, and interact with the web at scale. 🔥
TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…
Codebase for Aria - an Open Multimodal Native MoE
Local UI to run and train LLMs and diffusion models, including Kimi K3, MiniMax-H3, Gemma 4, Qwen3.6, DeepSeek-V4, FLUX and more.
Pytorch🍊🍉 is delicious, just eat it! 😋😋
A repository for research on medium sized language models.
ai副业赚钱大集合，教你如何利用ai做一些副业项目，赚取更多额外收益。The Ultimate Guide to Making Money with AI Side Hustles: Learn how to leverage AI for some cool side gigs and rake in some extra cash. Check out the English versi…
Perplexity Inspired Answer Engine
🙌 OpenHands: AI-Driven Development
A curated list of awesome LLM agents frameworks.
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
The open-source iOS app that's making quality voice transcription more accessible on mobile devices.
MiniCPM5-1B: A SOTA 1B on-device LLM, small yet powerful.
Modeling, training, eval, and inference code for OLMo
The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.