Starred repositories
Transformers-compatible library for applying various compression algorithms to LLMs for optimized deployment with vLLM
Write scalable load tests in plain Python 🚗💨
Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.
A unified library for building, evaluating, and storing speculative decoding algorithms for LLM inference in vLLM
Training Sparse Autoencoders on Language Models
DeepGEMM: clean and efficient BLAS kernel library on GPU
The agent that grows with you
🦙 LaMa Image Inpainting, Resolution-robust Large Mask Inpainting with Fourier Convolutions, WACV 2022
slime is an LLM post-training framework for RL Scaling.
Train speculative decoding models effortlessly and port them smoothly to SGLang serving.
Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).
AI agent toolkit: unified LLM API, agent loop, TUI, coding agent CLI
A library for accelerating Transformer models on NVIDIA GPUs, including using 8-bit and 4-bit floating point (FP8 and FP4) precision on Hopper, Ada and Blackwell GPUs, to provide better performance…
The most powerful local music generation model that outperforms almost all commercial alternatives, supporting Mac, AMD, Intel, and CUDA devices.
Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞
A cross-platform desktop All-in-One assistant for Claude Code, Codex, OpenCode, OpenClaw, Grok Build & Hermes Agent. Only official website: ccswitch.io
Claude Code is an agentic coding tool that lives in your terminal, understands your codebase, and helps you code faster by executing routine tasks, explaining complex code, and handling git workflo…
Unsloth is a local UI for training and running Gemma 4, Qwen3.6, DeepSeek, Kimi, GLM and other models.
A framework for few-shot evaluation of language models.
A Collection of BM25 Algorithms in Python
Translating Akkadian signs to transcriptions using NLP techniques such as HMM, MEMM and BiLSTM neural networks.
EasyR1: An Efficient, Scalable, Multi-Modality RL Training Framework based on veRL
verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework
verl-agent is an extension of veRL, designed for training LLM/VLM agents via RL. verl-agent is also the official code for paper "Group-in-Group Policy Optimization for LLM Agent Training"
Controlled text generation with programmable constraints