Highlights
- Pro
Stars
The open-source RAG platform: built-in citations, deep research, 22+ file formats, partitions, MCP server, and more.
Hackable and optimized Transformers building blocks, supporting a composable construction.
A Datacenter Scale Distributed Inference Serving Framework
Train transformer language models with reinforcement learning.
Public repository for "The Surprising Effectiveness of Test-Time Training for Abstract Reasoning"
General-purpose programming language and toolchain for maintaining robust, optimal, and reusable software.
Complete solutions to the Programming Massively Parallel Processors Edition 4
🪢 Open source LLM engineering platform: LLM Observability, metrics, evals, prompt management, playground, datasets. Integrates with OpenTelemetry, Langchain, OpenAI SDK, LiteLLM, and more. 🍊YC W23
An Easy-to-use, Scalable and High-performance RLHF Framework based on Ray (PPO & GRPO & REINFORCE++ & vLLM & Ray & Dynamic Sampling & Async Agentic RL)
Scalable toolkit for efficient model reinforcement
Scalable toolkit for efficient model alignment
Code for "WebVoyager: WebVoyager: Building an End-to-End Web Agent with Large Multimodal Models"
Universal memory layer for AI Agents; Announcing OpenMemory MCP - local and secure memory management.
verl: Volcano Engine Reinforcement Learning for LLMs
🌐 Make websites accessible for AI agents. Automate tasks online with ease.
A simple and efficient Mamba implementation in pure PyTorch and MLX.
CUDA Templates and Python DSLs for High-Performance Linear Algebra
An interference-aware scheduler for fine-grained GPU sharing
An extremely fast Python package and project manager, written in Rust.
SearXNG is a free internet metasearch engine which aggregates results from various search services and databases. Users are neither tracked nor profiled.
A Python module to scrape several search engines (like Google, Yandex, Bing, Duckduckgo, ...). Including asynchronous networking support.