Aya is an eBPF library for the Rust programming language, built with a focus on developer experience and operability.

Minimal reproduction of DeepSeek R1-Zero

An Easy-to-use, Scalable and High-performance Agentic RL Framework based on Ray (PPO & DAPO & REINFORCE++ & VLM & TIS & vLLM & Ray & Async RL)

Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.

ZenML 🙏: One AI Platform from Pipelines to Agents. https://zenml.io.

NVR with realtime local object detection for IP cameras

A storage plugin that provided CRI-O/Podman with the ability to lazy mount nydus images.

Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.

Delivers efficient, stable, and secure data distribution and acceleration powered by P2P technology, with an optional content‑addressable filesystem that accelerates OCI container launch.

MentraOS is the leading smart glasses platform + SDK. Stream your view, transcribe audio, talk to AI and capture photos hands-free on compatible glasses.

This is an ilogtail performance comparison repository

A high-performance RL training-inference weight synchronization framework, designed to enable second-level parameter updates from training to inference in RL workflows

agentUniverse is a LLM multi-agent framework that allows developers to easily build multi-agent applications.

A composable and fully extensible C++ execution engine library for data management systems.

A Kubernetes Provider

A portable Multimodal Lakehouse powered by Ray that brings exabyte-level scalability and fast, ACID-compliant, change-data-capture to your ML and analytics workloads.

A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

Data processing for and with foundation models! 🍎 🍋 🌽 ➡️ ➡️🍸 🍹 🍷

Serverless LLM Serving for Everyone.

🥥 Coco AI Server - Search, Connect, Collaborate, AI-powered Enterprise Search, all in one space.

A Cloud Native Batch System (Project under CNCF)

ClickHouse® is a real-time analytics database management system

Standardized Distributed Generative and Predictive AI Inference Platform for Scalable, Multi-Framework Deployment on Kubernetes

LLM training in simple, raw C/CUDA

High-performance data engine for AI and multimodal workloads. Process images, audio, video, and structured data at any scale

Pocket Flow: 100-line LLM framework. Let Agents build Agents!

时下热词追踪Agent 💡，集成多 Tools、TTS、ASR、HeyGem API

The most powerful and modular diffusion model GUI, api and backend with a graph/nodes interface.

Wan2.1 for Mac.