shimmy

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

Recent spike this week

7d +0.24% +14 stars in 7d
30d Not tracked yet — first tracked 2026-09-13
90d Not tracked yet — first tracked 2026-09-13
Sep 13, 2026: 5,867 starsSep 14, 2026: 5,869 starsSep 15, 2026: 5,882 starsSep 16, 2026: 5,884 starsSep 17, 2026: 5,886 starsSep 18, 2026: 5,890 starsSep 19, 2026: 5,891 starsSep 20, 2026: 5,895 starsSep 21, 2026: 5,903 starsSep 22, 2026: 5,905 starsSep 23, 2026: 5,904 starsSep 24, 2026: 5,903 starsSep 25, 2026: 5,905 starsSep 26, 2026: 5,908 starsSep 27, 2026: 5,907 starsSep 28, 2026: 5,906 starsSep 29, 2026: 5,909 starsSep 30, 2026: 5,914 starsOct 1, 2026: 5,917 stars 5,8675,8925,917 Sep 13Oct 1

5,867 → 5,917 stars since Sep 13

5,866 Stars 578 Forks 11 Open issues
api-servercommand-line-tooldeveloper-toolsggufhuggingfacehuggingface-modelshuggingface-transformersinference-serverllamallamacppllm-inferencelocal-aimachine-learningollama-apiopenai-compatiblerustrust-cratetransformerswebgpuwebgpu-shaders