{"slug":"inference","name":"inference","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://inference.readthedocs.io","repo":"https://github.com/xorbitsai/inference","latestVersion":"v3.5.0","latestRelease":"2026-09-25","stars":9623,"starsAsOf":"2026-10-22","description":"Swap GPT for any LLM by changing a single line of code. Xinference lets you run open-source, speech, and multimodal models on cloud, on-prem, or your laptop — all through one unified, production-ready inference API.","descriptionZh":"Xinference 分布式模型推理平台","callMethods":["API"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["artificial-intelligence","deployment","diffusers","gemma","glm","glm-5-3","inference","kimi","kimi-k3","llama-cpp","llamacpp","llm","machine-learning","openai-api","pytorch","qwen","sglang","transformers","vllm","whisper"],"language":"Python","lastPush":"2026-10-22","formerly":null,"packages":[],"recentVersions":[{"version":"v3.5.0","date":"2026-09-25","prerelease":false,"url":"https://github.com/xorbitsai/inference/releases/tag/v3.5.0","source":"GitHub Release"},{"version":"v3.4.0","date":"2026-09-11","prerelease":false,"url":"https://github.com/xorbitsai/inference/releases/tag/v3.4.0","source":"GitHub Release"},{"version":"v3.3.0","date":"2026-08-30","prerelease":false,"url":"https://github.com/xorbitsai/inference/releases/tag/v3.3.0","source":"GitHub Release"},{"version":"v3.2.1","date":"2026-08-17","prerelease":false,"url":"https://github.com/xorbitsai/inference/releases/tag/v3.2.1","source":"GitHub Release"},{"version":"v3.2.0","date":"2026-08-15","prerelease":false,"url":"https://github.com/xorbitsai/inference/releases/tag/v3.2.0","source":"GitHub Release"}],"alternatives":["gpustack","lmcache","kserve","llama-swap","ramalama","ncnn","ollama","koboldcpp"],"stacks":[],"scenarios":["switch-models","run-models-locally","use-ai-compliantly-in-china","learn-ai"],"problems":[],"reasonZh":"开源大库收录：Xinference 分布式模型推理平台","sources":["oss","github-pool"],"record":"https://aimap.page/api/v1/software/inference.json","pages":{"en":"https://aimap.page/en/software/inference/","zh-hans":"https://aimap.page/zh-hans/software/inference/"}}