Stars
分享AI Infra知识&代码练习：PyTorch/vLLM/SGLang框架入门⚡️、性能加速🚀、大模型基础🧠、AI软硬件🔧等
Ultra-high performance distributed storage system in the AI era. Powered by Fractal ART engine, Rust-native, io_uring, with multi-protocol (S3 object storage, POSIX FS, ...)
Cadence is a distributed, scalable, durable, and highly available orchestration engine to execute asynchronous long-running business logic in a scalable and resilient way.
AI agents running research on single-GPU nanochat training automatically
将冰冷的离别化为温暖的 Skill，欢迎加入数字生命1.0！Transforming cold farewells into warm skills? It's giving rebirth era. Welcome to Digital Life 1.0. 🫶
Techniques and numbers for estimating system's performance from first-principles
KAI Scheduler is an open source Kubernetes Native scheduler for AI workloads at large scale
A community trust management system based on explicit vouches to participate.
An agentic skills framework & software development methodology that works.
A platform that makes it easy for developers to build realtime, cost-effective, operations-focused applications
A Rust CPU profiler implemented with the help of backtrace-rs
dwm-inspired tiling pane management for tmux
A runtime for writing reliable asynchronous applications with Rust. Provides I/O, networking, scheduling, timers, ...
A simple, performant and scalable Jax LLM!
This is the Rust course used by the Android team at Google. It provides you the material to quickly teach Rust.
Production-Grade Container Scheduling and Management
AI-powered SRE platform for automated incident investigation
Bf-Tree is a modern read-write-optimized concurrent larger-than-memory range index in Rust from MS Research.
Gossip-based service discovery (and more) for large distributed systems.
ClickHouse® is a real-time analytics database management system
Code from various chapters in OSTEP (http://www.ostep.org)
🚀 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…
The simplest way to serve AI/ML models in production
Supercharge Your LLM with the Fastest KV Cache Layer