gpustack/gpustack

A GPU cluster manager for high-performance AI model serving (vLLM, SGLang) and on-demand SSH-accessible GPU instances.

语言：Python · GitHub 星标：5,977 · Fork：722

话题：ascend · cuda · deepseek · distributed-inference · genai · high-performance-inference · inference · llama

在 GitHub 上查看原仓库