{"slug":"gpustack","name":"gpustack","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://gpustack.ai","repo":"https://github.com/gpustack/gpustack","latestVersion":"v2.2.3","latestRelease":"2026-07-31","stars":5870,"starsAsOf":"2026-10-22","description":"A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.","descriptionZh":"GPU 集群模型部署管理","callMethods":["API"],"platforms":[],"addedAt":"2026-10-10","updatedAt":"2026-10-22","topics":["ascend","cuda","deepseek","distributed-inference","genai","high-performance-inference","inference","llama","llm","llm-inference","llm-serving","maas","mindie","openai","qwen","rocm","sglang","vllm"],"language":"Python","lastPush":"2026-10-22","formerly":null,"packages":[],"recentVersions":[{"version":"v2.2.3","date":"2026-07-31","prerelease":false,"url":"https://github.com/gpustack/gpustack/releases/tag/v2.2.3","source":"GitHub Release"},{"version":"v2.2.2","date":"2026-07-24","prerelease":false,"url":"https://github.com/gpustack/gpustack/releases/tag/v2.2.2","source":"GitHub Release"},{"version":"v2.2.1","date":"2026-07-03","prerelease":false,"url":"https://github.com/gpustack/gpustack/releases/tag/v2.2.1","source":"GitHub Release"},{"version":"v2.2.0","date":"2026-06-18","prerelease":false,"url":"https://github.com/gpustack/gpustack/releases/tag/v2.2.0","source":"GitHub Release"}],"alternatives":["lmcache","inference","vllm","sglang","lmdeploy","llama-swap","llm-d","ramalama"],"stacks":[],"scenarios":["switch-models","run-models-locally","use-ai-compliantly-in-china","learn-ai"],"problems":[],"reasonZh":"GPU 集群管理，支持国产卡（推断）","sources":["priority","oss","github-oss","github-pool"],"record":"https://aimap.page/api/v1/software/gpustack.json","pages":{"en":"https://aimap.page/en/software/gpustack/","zh-hans":"https://aimap.page/zh-hans/software/gpustack/"}}