A simple, performant, and scalable Jax LLM!

Integrate the DeepSeek API into popular software

An open-source long-horizon SuperAgent harness that researches, codes, and creates. With the help of sandboxes, memories, tools, skill, subagents and message gateway, it handles different levels of…

Build an agent harness and control it end-to-end. Open-source SDK for production AI agents in Python & TypeScript - any model, any cloud.

Train speculative decoding models effortlessly and port them smoothly to SGLang serving.

An interface library for RL post training with environments.

Ongoing research training transformer models at scale

An open-source AI agent that brings the power of Gemini directly into your terminal.

Code, labs, and resources for O'Reilly AI Systems Performance Engineering: GPU optimization, distributed training, inference scaling, and full-stack tuning.

[JMLR (CCF-A)] PyPop7: A Pure-PYthon LibrarY for POPulation-based Black-Box Optimization (BBO), especially *Large-Scale* algorithm variants. In the near future, we will add Learning-Based Optimizer…

[NeurIPS'21 Outstanding Paper] Library for reliable evaluation on RL and ML benchmarks, even with only a handful of seeds.

An Efficient and User-Friendly Scaling Library for Reinforcement Learning with Large Language Models

TensorZero is an open-source LLMOps platform that unifies an LLM gateway, observability, evaluation, optimization, and experimentation.

A list of papers regarding generalization in (deep) reinforcement learning

LMCache: Supercharge Your LLM with the Fastest KV Cache Layer

1 million FPS multi-agent driving simulator

Puffing up reinforcement learning

Hardware-Accelerated Reinforcement Learning Algorithms in pure Jax!

Isaac Gym Reinforcement Learning Environments

🚀 Awesome System for Machine Learning ⚡️ AI System Papers and Industry Practice. ⚡️ System for Machine Learning, LLM (Large Language Model), GenAI (Generative AI). 🍻 OSDI, NSDI, SIGCOMM, SoCC, MLSy…

[EMNLP 2025 Demo] Extracting internal representations from vision-language models. Beta version.

A programmable Mixture-of-Models router for heterogeneous LLM inference

A benchmark for LLMs on complicated tasks in the terminal

Democratizing Reinforcement Learning for LLMs

[NeurIPS'25] Official codebase for "SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution"

Sparsity-aware deep learning inference runtime for CPUs

ALIEN is a CUDA-powered artificial life simulation program.

Robust Speech Recognition via Large-Scale Weak Supervision

Synchronized Curriculum Learning for RL Agents