Michael-A-Kuykendall/shimmy

⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.

语言：Rust · GitHub 星标：6,012 · Fork：587

话题：api-server · command-line-tool · developer-tools · gguf · huggingface · huggingface-models · huggingface-transformers · inference-server

在 GitHub 上查看原仓库