{"slug":"lmcache","name":"LMCache","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://lmcache.ai/","repo":"https://github.com/LMCache/LMCache","latestVersion":"v0.5.6","latestRelease":"2026-10-16","stars":12145,"starsAsOf":"2026-10-22","description":"LMCache: Supercharge Your LLM with the Fastest KV Cache Layer","descriptionZh":"LLM KV 缓存层加速","callMethods":["SDK"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["amd","cuda","fast","inference","kv-cache","llm","pytorch","rocm","speed","vllm"],"language":"Python","lastPush":"2026-10-22","formerly":null,"packages":[{"registry":"pypi","name":"lmcache","url":"https://pypi.org/project/lmcache/","versionsUrl":"https://pypi.org/project/lmcache/#history","latestVersion":"0.5.5","latestDate":"2026-09-12"}],"recentVersions":[{"version":"v0.5.6rc3-cu129","date":"2026-10-07","prerelease":false,"url":"https://github.com/LMCache/LMCache/releases/tag/v0.5.6rc3-cu129","source":"GitHub Release"},{"version":"v0.5.6rc3-rocm","date":"2026-10-06","prerelease":false,"url":"https://github.com/LMCache/LMCache/releases/tag/v0.5.6rc3-rocm","source":"GitHub Release"},{"version":"v0.5.6rc3-rocm-torch210","date":"2026-10-06","prerelease":false,"url":"https://github.com/LMCache/LMCache/releases/tag/v0.5.6rc3-rocm-torch210","source":"GitHub Release"},{"version":"v0.5.6rc3-musa","date":"2026-10-06","prerelease":false,"url":"https://github.com/LMCache/LMCache/releases/tag/v0.5.6rc3-musa","source":"GitHub Release"},{"version":"v0.5.6rc2-cu129","date":"2026-09-28","prerelease":false,"url":"https://github.com/LMCache/LMCache/releases/tag/v0.5.6rc2-cu129","source":"GitHub Release"}],"alternatives":["gpustack","inference","vllm","ramalama","sglang","tensorrt-llm","llm-d","ncnn"],"stacks":[],"scenarios":["switch-models","run-models-locally","use-ai-compliantly-in-china","learn-ai"],"problems":[],"reasonZh":"开源大库收录：LLM KV 缓存层加速","sources":["oss","github-oss","github-pool"],"record":"https://aimap.page/api/v1/software/lmcache.json","pages":{"en":"https://aimap.page/en/software/lmcache/","zh-hans":"https://aimap.page/zh-hans/software/lmcache/"}}