Michael-A-Kuykendall/shimmy

Michael-A-Kuykendall/shimmy

GitHubGitHub
GitHubgithub.com
Releases44
Frequency1 week 9 hours
Last Release
Stars5.68K
⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
Log in to subscribe

Linked projects

shimmy
Lightweight Ollama-compatible inference server with native SafeTensors support. No Python dependencies, cross-platform WebGPU acceleration via Airframe.