RLinf: Reinforcement Learning Infrastructure for Embodied and Agentic AI

SGLang is a fast serving framework for large language models and vision language models.

[Experimental] Miles-diffusion is an post-training framework for large-scale diffusion model training and production workloads, forked from and co-evolving with miles.

2025 & 2026 New grad full-time roles in SWE, Quant, and PM.

Node-based visual tool for building and inspecting ML models

slime is an LLM post-training framework for RL Scaling.

The agent that grows with you

Lightweight coding agent that runs in your terminal

This is the official repository of paper: Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation.

The original nirholas/claude-code before DMCA and take down. Once everything is cleared, it will return. Working with Anthropic and Github to get everything back.

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…

Blackwell GEMM Kernel Optimization

verl/HybridFlow: A Flexible and Efficient RL Post-Training Framework

🤗 Diffusers: State-of-the-art diffusion models for image, video, and audio generation in PyTorch.

A demonstrative example of running SGLang Diffusion with DP router

The SDK For Browser Agents

Open-source, vision-first browser agent

A unified inference and post-training framework for accelerated video generation.

Multi-Agent Harness for Production AI

agent-sandbox enables easy management of isolated, stateful, singleton workloads, ideal for use cases like AI agent runtimes.

The BusTub Relational Database Management System (Educational)

Miles is an enterprise-facing reinforcement learning framework for large-scale MoE post-training and production workloads, forked from and co-evolving with slime.

Miles is an enterprise-facing reinforcement learning framework for large-scale MoE post-training and production workloads, forked from and co-evolving with slime.

Qwen3-omni is a natively end-to-end, omni-modal LLM developed by the Qwen team at Alibaba Cloud, capable of understanding text, audio, images, and video, as well as generating speech in real time.

Miles is an enterprise-facing reinforcement learning framework for LLM and VLM post-training, forked from and co-evolving with slime.

A user-space file system for interacting with Google Cloud Storage