DeepSeek Harness: Everything is a Plugin.

MindOS is a Human-AI Collaborative Mind System, where human thinks and agents act. Globally sync your mind for all agents: transparent, controllable, and evolving symbiotically.

The code of our paper "Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding" accepted by KDD2025

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

DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.

The official repository for "Rongsheng Wang's Arxiv Template"

GENERator: A Long-Context Generative Genomic Foundation Model

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

MLGym A New Framework and Benchmark for Advancing AI Research Agents

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

🙌 OpenHands: AI-Driven Development

Code for Paper: Training Software Engineering Agents and Verifiers with SWE-Gym [ICML 2025]

SWE-bench: Can Language Models Resolve Real-world Github Issues?

🌍 AppWorld: A Controllable World of Apps and People for Benchmarking Function Calling and Interactive Coding Agent, ACL'24 Best Resource Paper.

🤗 smolagents: a barebones library for agents that think in code.

GENERanno: A Genomic Foundation Model for Metagenomic Annotation

Code for BLT research paper

AgentTuning: Enabling Generalized Agent Abilities for LLMs

DSPy: The framework for programming—not prompting—language models

FlashInfer: Kernel Library for LLM Serving

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

Survey: A collection of AWESOME papers and resources on the large language model (LLM) related recommender system topics.

📰 Must-read papers and blogs on LLM based Long Context Modeling 🔥

Ring attention implementation with flash attention

Implementation of 💍 Ring Attention, from Liu et al. at Berkeley AI, in Pytorch

The code of our paper "InfLLM: Unveiling the Intrinsic Capacity of LLMs for Understanding Extremely Long Sequences with Training-Free Memory"

The code of our paper "AFDGCF: Adaptive Feature De-correlation Graph Collaborative Filtering for Recommendations" accepted by SIGIR2024

Saprot: Protein Language Model with Structural Alphabet (AA+3Di)