Kubernetes AI Toolchain Operator

The source for REST API specifications for Microsoft Azure.

Evaluating an inference stack built on top of KAITO and llm-d.

Tinycast — a tiny, fully native macOS launcher, hotkeys, and clipboard history

Offline optimization of your disaggregated Dynamo graph

DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling

Supercharge Your LLM with the Fastest KV Cache Layer

Lightweight coding agent that runs in your terminal

verl: Volcano Engine Reinforcement Learning for LLMs

Your 24/7 On-Call AI Agent - Solve Alerts Faster with Automatic Correlations, Investigations, and More

SGLang is a fast serving framework for large language models and vision language models.

A high-throughput and memory-efficient inference and serving engine for LLMs

local-csi-driver provides access to local NVMe storage from Kubernetes

An open and reliable container runtime

Production-Grade Container Scheduling and Management

The Go programming language

tools to create and extract Squashfs filesystems

cricket is a virtualization solution for GPUs

contaiNERD CTL - Docker-compatible CLI for containerd, with support for Compose, Rootless, eStargz, OCIcrypt, IPFS, ...

cgroups package for Go

Official Java client library for kubernetes

OpenAPI extension in Go for the go-restful package

Crane (FinOps Crane) is an opensource project which manages cloud resource on Kubernetes stack, it is inspired by FinOps concepts.