TPU inference for vLLM, with unified JAX and PyTorch support.

JAX backend for SGL

100M tokens. Infinite compute. Lowest val loss wins.

Run more RL experiments. Wait less for GPUs.

Expert Parallelism Load Balancer

An interface library for RL post training with environments.

The open source coding agent.

A set of examples based on verl for end-to-end RL training recipes.

An Extensible Deep Learning Library

Official Code for "Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search"

Official implement on InternBootCamp

SSRL: Self-Search Reinforcement Learning

A Lightweight LLM Post-Training Library

MiroRL is an MCP-first reinforcement learning framework for deep research agent.

[ICLR 2026] "Co-rewarding: Stable Self-supervised RL for Eliciting Reasoning in Large Language Models"

[ICLR 2026] SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning

A Gym for Agentic LLMs

A repo for open research on building large reasoning models

SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward

[NeurIPS 2025] NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation

[ICLR'26] RM-R1: Unleashing the Reasoning Potential of Reward Models

Repository for the paper "InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners"

The absolute trainer to light up AI agents.

VeOmni: Scaling Any Modality Model Training with Model-Centric Distributed Recipe Zoo