Stars
An Open Phone Agent Model & Framework. Unlocking the AI Phone for Everyone
Official implementation of GRAPE: Group Representational Position Encoding (https://arxiv.org/abs/2512.07805)
[ICCV'25] The official code of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"
SGLang is a high-performance serving framework for large language models and multimodal models.
A reproduction of the Deepseek-OCR model including training
Cambrian-S: Towards Spatial Supersensing in Video
Minimal yet performant LLM examples in pure JAX
(best/better) practices of megatron on veRL and tuning guide
🔥 LLM-powered GPU kernel synthesis: Train models to convert PyTorch ops into optimized Triton kernels via SFT+RL. Multi-turn compilation feedback, cross-platform NVIDIA/AMD, Kernelbook + KernelBench
slime is an LLM post-training framework for RL Scaling.
MLX-VLM is a package for inference and fine-tuning of Vision Language Models (VLMs) on your Mac using MLX.
RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI
State-of-the-art Image & Video CLIP, Multimodal Large Language Models, and More!
Implementation for FP8/INT8 Rollout for RL training without performence drop.
Reading notes about Multimodal Large Language Models, Large Language Models, and Diffusion Models
Pioneering Automated GUI Interaction with Native Agents
GEO-Bench: Toward Foundation Models for Earth Monitoring
Build Flash Attention wheels for NVIDIA clusters
Muon is an optimizer for hidden layers in neural networks
The development and future prospects of large multimodal reasoning models.
Unleashing the Power of Reinforcement Learning for Math and Code Reasoners
【CVPR 2025 Oral】Official Repo for Paper "AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea"
Meta Lingua: a lean, efficient, and easy-to-hack codebase to research LLMs.
The official repo of One RL to See Them All: Visual Triple Unified Reinforcement Learning
FlashInfer: Kernel Library for LLM Serving
Build and host decentralized blogs and websites on your Mac
[NeurIPS 2025 Spotlight] Reasoning Environments for Reinforcement Learning with Verifiable Rewards