MLGym A New Framework and Benchmark for Advancing AI Research Agents

This repo contains the dataset and code for the paper "SWE-Lancer: Can Frontier LLMs Earn $1 Million from Real-World Freelance Software Engineering?"

SOTA RL fine-tuning solution for advanced math reasoning of LLM

Community maintained hardware plugin for vLLM on Ascend

Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.

AIInfra（AI 基础设施）指AI系统从底层芯片等硬件，到上层软件栈支持AI大模型训练和推理。

Official Repo for Open-Reasoner-Zero

MoBA: Mixture of Block Attention for Long-Context LLMs

PaSa -- an advanced paper search agent powered by large language models. It can autonomously make a series of decisions, including invoking search tools, reading papers, and selecting relevant refe…

My learning notes/codes for ML SYS.

An open-source cross-platform alternative to AirDrop

A very simple GRPO implement for reproducing r1-like LLM thinking.

Codebase for Iterative DPO Using Rule-based Rewards

A simple calculation for LLM MFU.

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

Sandboxed code execution for AI agents, locally or on the cloud.

CodeI/O: Condensing Reasoning Patterns via Code Input-Output Prediction

Democratizing Reinforcement Learning for LLMs

An AI-powered research assistant that performs iterative, deep research on any topic by combining search engines, web scraping, and large language models. The goal of this repo is to provide the si…

An open source deep research clone. AI Agent that reasons large amounts of web data extracted with Firecrawl

DeepSeek 系列工作解读、扩展和复现。

🤗 smolagents: a barebones library for agents. Agents write python code to call tools and orchestrate other agents.

Reproduce R1 Zero on Logic Puzzle

Experiments on Multi-Head Latent Attention

s1: Simple test-time scaling

A fast and lightweight fully featured OCI runtime and C library for running containers

Linux running inside a PDF file via a RISC-V emulator