Stars
System Level Intelligent Router for Mixture-of-Models
Wish your friend/loved-ones happy birthday in a nerdy way.
iFlow cli is a comprehensive command-line intelligence that embeds in your terminal, analyzes your repositories, does coding tasks, interprets your needs across contexts, and boosts efficiency by p…
Distributed KV cache scheduling & offloading libraries
Enable Acrylic/Glass effect for your VS Code.
Exponentially Weighted Moving Average algorithms for Go.
LLM Semantic Router: Intelligent Mixture-of-Models (MoM) System with Privacy Preservation and Prompt Guard. The semantic router intelligently directs OpenAI compliant API requests to the most suita…
Achieve state of the art inference performance with modern accelerators on Kubernetes
Gateway API Inference Extension
QiZhenGPT: An Open Source Chinese Medical Large Language Model｜一个开源的中文医疗大语言模型
No fortress, purely open ground. OpenManus is Coming.
Cost-efficient and pluggable Infrastructure components for GenAI inference
你管这破玩意叫操作系统源码 — 像小说一样品读 Linux 0.11 核心代码
High Performance ServiceMesh Data Plane Based on eBPF and Programmable Kernel
A tutorial to scale Websockets both via Docker Swarm and Kubernetes
The container platform tailored for Kubernetes multi-cloud, datacenter, and edge management ⎈ 🖥 ☁️
Kubernetes-based, scale-to-zero, request-driven compute
OpenYurt - Extending your native Kubernetes to edge(project under CNCF)
torchserve example for style transfer
Fluid, elastic data abstraction and acceleration for BigData/AI applications in cloud. (Project under CNCF)
LazyXds enables Istio only push needed xDS to sidecars to reduce resource consumption and speed up xDS configuration propagation.
Build, Share and Run Both Your Kubernetes Cluster and Distributed Applications (Project under CNCF)