sky

SGLang is a high-performance serving framework for large language models and multimodal models.

Distributed Compiler based on Triton for Parallel Systems

cuTile is a programming model for writing parallel kernels for NVIDIA GPUs

Optimized primitives for collective multi-GPU communication

DeepXTrace is a lightweight tool for precisely diagnosing slow ranks in DeepEP-based environments.

DeepEP: an efficient expert-parallel communication library

Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels

MOSN is a powerful cloud-native proxy acts as a edge proxy or service mesh's data plane. https://mosn.io

C++ front/service proxy

Community maintained hardware plugin for vLLM on Ascend

A sample project that exists for PyPUG's "Tutorial on Packaging and Distributing Projects"

Machine management for a container-centric world

A distribution of Nginx with some advanced features

Official NGINX Dockerfiles

There is my blog and record about some study

NCCL Fast Socket is a transport layer plugin to improve NCCL collective communication performance on Google Cloud.

No description provided.

docker error 403

An experimental implementation of the `ztunnel` component of ambient mesh

evnoy with go extension

Redis is an in-memory database that persists on disk. The data model is key-value, but many different kind of values are supported: Strings, Lists, Sets, Sorted Sets, Hashes, Streams, HyperLogLogs, Bitmaps.

High-performance WAF built on the OpenResty stack

Use eBPF to speed up your Service Mesh like crossing an Einstein-Rosen Bridge.

a nice library to hook golang function at runtime

Simple network namespace handling for go.

Source for mosn.io site

Tutorial for MOSN and Istio Service Mesh - https://www.katacoda.com/mosn

Connect, secure, control, and observe services.

Swarm: a Docker-native clustering system

An open-source and enterprise-level monitoring system.