Lists (8)
Starred repositories
An inference control plane for Kubernetes and vLLM
10BC8
Provider-neutral Kubernetes APIs and core controllers for virtual machine lifecycle management
Self-service manage your virtual infrastructure...
Welcome to the official repository for the Cloud Native Computing Foundation (CNCF) Governing Board.
Cloud native observability for the high-speed AI networks.
A high-level Kubernetes control layer for managing workload outcomes and disruption guardrails during maintenance.
Agent skill: make LLMs write docs in ASD-STE100 Simplified Technical
Tiered shared KV cache storage for LLM inference. Extends GPU HBM to host memory, NVMe, and JBOF pools — enabling cross-instance prefix reuse for vLLM, Dynamo, and NIXL.
https://pacoxu.github.io/football-research-sandbox/overseas.html
Humming is a high-performance, lightweight, and highly flexible JIT (Just-In-Time) compiled GEMM kernel library specifically designed for quantized inference.
AISimulate predicts LLM serving behavior and searches for strong deployment configurations offline, without bringing up a GPU serving cluster
The control plane for GPUaaS — across neoclouds, hyperscalers, and your own infrastructure.
DeepSeek Harness: Everything is a Plugin.
An Open-source, self-hosted AI model hub with Hugging Face compatibility, accelerating vLLM/SGLang performance.
Insights into the world's most critical open source software.
🛰️ Track token usage across AI coding agents from your terminal. 🏅 Global leaderboard with trillions of tokens tracked.
A set of reference agents for executing operational and DevOps tasks across diverse infrastructure platforms.
7
Updated May 15, 2026
A community database for the problems on the erdosproblems.com site
Open Source AI Accelerator Research Platform Standard / 开源推理研究平台
Switch agents. Keep the history. Local-first search across your AI coding sessions.