{"slug":"distributed-llama","name":"distributed-llama","category":"local-inference","categoryName":"Local inference & serving","audience":["ai-era"],"primary":"ai-era","openClosed":"open","pricing":"open-source","license":"MIT","maintained":"yes","officialUrl":"https://github.com/b4rtaz/distributed-llama","repo":"https://github.com/b4rtaz/distributed-llama","latestVersion":"v0.16.5","latestRelease":"2026-02-02","stars":3112,"starsAsOf":"2026-10-22","description":"Distributed LLM inference. Connect home devices into a powerful cluster to accelerate LLM inference. More devices means faster inference.","descriptionZh":"多设备分布式 LLM 推理","callMethods":["CLI"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["distributed-computing","distributed-llm","llama2","llama3","llm","llm-inference","llms","neural-network","open-llm"],"language":"C++","lastPush":"2026-10-14","formerly":null,"packages":[],"recentVersions":[{"version":"v0.16.5","date":"2026-02-02","prerelease":false,"url":"https://github.com/b4rtaz/distributed-llama/releases/tag/v0.16.5","source":"GitHub Release"},{"version":"v0.16.4","date":"2026-01-17","prerelease":false,"url":"https://github.com/b4rtaz/distributed-llama/releases/tag/v0.16.4","source":"GitHub Release"},{"version":"v0.16.3","date":"2025-10-26","prerelease":false,"url":"https://github.com/b4rtaz/distributed-llama/releases/tag/v0.16.3","source":"GitHub Release"},{"version":"v0.16.2","date":"2025-09-20","prerelease":false,"url":"https://github.com/b4rtaz/distributed-llama/releases/tag/v0.16.2","source":"GitHub Release"},{"version":"v0.16.1","date":"2025-09-16","prerelease":false,"url":"https://github.com/b4rtaz/distributed-llama/releases/tag/v0.16.1","source":"GitHub Release"}],"alternatives":["lmdeploy","gpustack","bentoml","ai-dynamo-dynamo","lms","llm-d","ramalama","ncnn"],"stacks":[],"scenarios":["switch-models","run-models-locally","use-ai-compliantly-in-china","learn-ai"],"problems":[],"reasonZh":"开源大库收录：多设备分布式 LLM 推理","sources":["oss","github-pool"],"record":"https://aimap.page/api/v1/software/distributed-llama.json","pages":{"en":"https://aimap.page/en/software/distributed-llama/","zh-hans":"https://aimap.page/zh-hans/software/distributed-llama/"}}