Lists (1)
Stars
SGLang is a high-performance serving framework for large language models and multimodal models.
A compact implementation of SGLang, designed to demystify the complexities of modern LLM serving systems.
Harbor is a framework for running agent evaluations and creating and using RL environments.
Seamless operability between C++11 and Python
SkyRL: A Modular Full-stack RL Library for LLMs
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
Research code artifacts for Code World Model (CWM) including inference tools, reproducibility, and documentation.
A clean, modular SDK for building AI agents with OpenHands V1.
A cross platform way to express data transformation, relational algebra, standardized record expression and plans.
Nydus - the Dragonfly image service, providing fast, secure and easy access to container images.
Textbook on reinforcement learning from human feedback
GRPO training code which scales to 32xH100s for long horizon terminal/coding tasks. Base agent is now the top Qwen3 agent on Stanford's TerminalBench leaderboard.
A benchmark for LLMs on complicated tasks in the terminal
A composable and fully extensible C++ execution engine library for data management systems.
[Up-to-date] Large Language Model Agent: A Survey on Methodology, Applications and Challenges
Gluten is a middle layer responsible for offloading JVM-based SQL engines' execution to native engines.
An incremental parsing system for programming tools
DeepSpeed is a deep learning optimization library that makes distributed training and inference easy, efficient, and effective.
JanusGraph web-based visualization tool
Playwright is a framework for Web Testing and Automation. It allows testing Chromium, Firefox and WebKit with a single API.
Implement a ChatGPT-like LLM in PyTorch from scratch, step by step
MSVC's implementation of the C++ Standard Library.
An agent benchmark with tasks in a simulated software company.
A high-throughput and memory-efficient inference and serving engine for LLMs
Supplementary materials and Implementation codes of Integrating Data Lake Tables (ALITE)
SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]