SGLang is a high-performance serving framework for large language models and multimodal models.

Lightning-Fast RL for LLM Reasoning and Agents. Made Simple & Flexible.

[ICML 2025] An official source code for paper "FlipAttack: Jailbreak LLMs via Flipping".

Improved techniques for optimization-based jailbreaking on large language models (ICLR2025)

An open platform for training, serving, and evaluating large language models. Release repo for Vicuna and Chatbot Arena.

一个开源的GPU服务器管理平台；可以实时查看模型训练状态、GPU资源占用、模型训练日志、IP访问记录等

Homepage for An

Minimal reproduction of OneRec

Code for the paper "VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment"

collecting publicly available distillation datasets based on DepSeek-R1

Fast and memory-efficient exact attention

[NeurIPS 2025] VeriThinker: Learning to Verify Makes Reasoning Model Efficient

A high-throughput and memory-efficient inference and serving engine for LLMs

A Unified Framework for High-Performance and Extensible LLM Steering

[COLM 2025] SEAL: Steerable Reasoning Calibration of Large Language Models for Free

Code for "Critique Fine-Tuning: Learning to Critique is More Effective than Learning to Imitate" [COLM 2025]

Code for paper "The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning"

An open protocol enabling communication and interoperability between opaque agentic applications.

[ACL 2024] The official codebase for the paper "Self-Distillation Bridges Distribution Gap in Language Model Fine-tuning".

[ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.

[NeurIPS 2025] Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning

USTC 大数据系统及综合实验大作业

personal web

Automated tool for running Python programs in a streamlined manner

SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis

[ICLR 2025 Oral 🏆] The implementation of paper "Language Representations Can be What Recommenders Need: Findings and Potentials"

[SIGIR 2024 perspective] The implementation of paper "On Generative Agents in Recommendation"

verl: Volcano Engine Reinforcement Learning for LLMs