{"slug":"lmdeploy","name":"lmdeploy","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://lmdeploy.readthedocs.io/en/latest","repo":"https://github.com/InternLM/lmdeploy","latestVersion":"v0.18.0","latestRelease":"2026-09-28","stars":8111,"starsAsOf":"2026-10-22","description":"LMDeploy is a toolkit for compressing, deploying, and serving LLMs.","descriptionZh":"LLM 压缩、部署与服务工具包","callMethods":["API","CLI"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["codellama","cuda-kernels","deepspeed","fastertransformer","internlm","llama","llama2","llama3","llm","llm-inference","turbomind"],"language":"Python","lastPush":"2026-10-22","formerly":null,"packages":[{"registry":"pypi","name":"lmdeploy","url":"https://pypi.org/project/lmdeploy/","versionsUrl":"https://pypi.org/project/lmdeploy/#history","latestVersion":"0.18.0","latestDate":"2026-09-28"}],"recentVersions":[{"version":"v0.18.0","date":"2026-09-28","prerelease":false,"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.18.0","source":"GitHub Release"},{"version":"v0.17.0","date":"2026-09-01","prerelease":false,"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.17.0","source":"GitHub Release"},{"version":"v0.16.0","date":"2026-08-19","prerelease":false,"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.16.0","source":"GitHub Release"},{"version":"v0.15.0","date":"2026-07-31","prerelease":false,"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.15.0","source":"GitHub Release"},{"version":"v0.14.0","date":"2026-06-24","prerelease":false,"url":"https://github.com/InternLM/lmdeploy/releases/tag/v0.14.0","source":"GitHub Release"}],"alternatives":["distributed-llama","gpustack","ollama","koboldcpp","bentoml","ai-dynamo-dynamo","llama-swap","lms"],"stacks":[],"scenarios":["switch-models","run-models-locally","use-ai-compliantly-in-china","learn-ai"],"problems":[],"reasonZh":"国产推理部署","sources":["priority","oss","github-pool"],"record":"https://aimap.page/api/v1/software/lmdeploy.json","pages":{"en":"https://aimap.page/en/software/lmdeploy/","zh-hans":"https://aimap.page/zh-hans/software/lmdeploy/"}}