Stars
This project aims to collect the latest "call for reviewers" links from various top CS/ML/AI conferences/journals
[NSDI'26] PolyRL is a reinforcement learning framework for LLM that harvest spot instances on the cloud to reduce cost.
Tile primitives for speedy kernels
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
分享AI Infra知识&代码练习：PyTorch/vLLM/SGLang框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等
NexRL is an ultra-loosely-coupled LLM post-training framework.
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
A toolkit for developing and comparing reinforcement learning algorithms.
A NCCL extension library, designed to efficiently offload GPU memory allocated by the NCCL communication library.
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
A set of examples based on verl for end-to-end RL training recipes.
Virtualized Elastic KV Cache for Dynamic GPU Sharing and Beyond
Long-RL: Scaling RL to Long Sequences (NeurIPS 2025)
Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.
An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models
Ideas for projects related to Tinker
Unsloth Studio is a web UI for training and running open models like Gemma 4, Qwen3.6, DeepSeek, gpt-oss locally.
Kimi K2 is the large language model series developed by Moonshot AI team
Virtual whiteboard for sketching hand-drawn like diagrams
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
Post-training with Tinker
Checkpoint-engine is a simple middleware to update model weights in LLM inference engines