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

[WIP] Pure-Go implementation of ZeroMQ-4

Latency prediction service for ML-model based scoring with llm-d-inference-scheduler

llm-d Router: The intelligent entry point for inference requests

Kubernetes community content

⌥ Coding agent with the IDE wired in

NVIDIA open GPU kernel modules with DGX Spark GB10 patches

Unbounded context. Memory that manages itself. One session, for life. The hippocampus for coding agents, part of CortexKit.

Give your agent a proper IDE and OS. The sensorimotor cortex for coding agents (OpenCode + Pi), part of CortexKit: symbol-aware edits, semantic search, code health, fast grep/glob, bash compression…

FlashInfer: Kernel Library for LLM Serving

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

vLLM Quantization plugin for GGUF

AI Tensor Engine for ROCm

The open source coding agent.

OpenCode release integration watcher

Home for the cluster api work, a subproject of sig-cluster-lifecycle

User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

trust-manager is an operator for distributing trust bundles across a Kubernetes cluster.

Automatically provision and manage TLS certificates in Kubernetes

Kubernetes IN Docker - local clusters for testing Kubernetes