{"slug":"llm-d","name":"llm-d","category":"local-inference","categoryName":"Local inference & serving","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"Apache-2.0","maintained":"yes","officialUrl":"https://www.llm-d.ai","repo":"https://github.com/llm-d/llm-d","latestVersion":"v1.0.0","latestRelease":"2026-10-20","stars":4967,"starsAsOf":"2026-10-23","description":"Achieve state of the art inference performance with modern accelerators on Kubernetes","descriptionZh":"Kubernetes 原生分布式推理","callMethods":["API"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-23","topics":["ai","cncf","distributed-inference","gpu","inference","intelligent-routing","kubernetes","llm"],"language":"Python","lastPush":"2026-10-22","formerly":null,"packages":[],"recentVersions":[{"version":"v0.10","date":"2026-09-29","prerelease":false,"url":"https://github.com/llm-d/llm-d/releases/tag/v0.10","source":"GitHub Release"},{"version":"v0","date":"2026-09-29","prerelease":false,"url":"https://github.com/llm-d/llm-d/releases/tag/v0","source":"GitHub Release"},{"version":"v0.10.0","date":"2026-09-29","prerelease":false,"url":"https://github.com/llm-d/llm-d/releases/tag/v0.10.0","source":"GitHub Release"},{"version":"v0.9.0","date":"2026-08-17","prerelease":false,"url":"https://github.com/llm-d/llm-d/releases/tag/v0.9.0","source":"GitHub Release"},{"version":"v0.9","date":"2026-08-13","prerelease":false,"url":"https://github.com/llm-d/llm-d/releases/tag/v0.9","source":"GitHub Release"}],"alternatives":["gpustack","ramalama","lmcache","triton-inference-server-server","openvino","inference","vllm","flashinfer"],"stacks":[],"scenarios":["switch-models","run-models-locally","use-ai-compliantly-in-china","learn-ai"],"problems":[],"reasonZh":"Red Hat AI Inference 配合 llm-d","sources":["profile","priority","oss","github-oss","github-pool"],"record":"https://aimap.page/api/v1/software/llm-d.json","pages":{"en":"https://aimap.page/en/software/llm-d/","zh-hans":"https://aimap.page/zh-hans/software/llm-d/"}}