truespar/paddock

Native Rust inference server for open models on NVIDIA and Apple Silicon. OpenAI- and Anthropic-compatible APIs, GGUF + safetensors + MLX, FP8/NVFP4/MXFP4/Q8/Q4, built-in Studio

语言：Rust · GitHub 星标：149 · Fork：22

话题：ai · aimodels · blackwell · cuda · inference · inference-engine · inference-optimization · macos

在 GitHub 上查看原仓库