Sign in Sign up
cargo

shimmy

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

Activity

Latest release
2w ago
Total releases
34
Cadence
~2 days
Last 12 months
23

Reach

Downloads
13.1k
Stars
5.8k

Details

License
MIT
First release
Sep 04, 2025
Releases
Version Released
2.6.4 patch
2.6.3 patch
2.6.2 patch
2.6.1 patch
2.6.0 minor
2.5.0 minor
2.4.2 patch
2.4.0 minor
2.3.3 patch
2.3.2 patch
2.3.1 patch
2.3.0 minor
2.1.1 minor
2.2.0 minor
2.0.1 patch
2.0.0 major
1.9.0 minor yanked
1.8.2 patch yanked
1.8.1 minor
1.7.4 patch
1.7.3 patch
1.7.0 minor
1.6.0 minor
1.4.2 patch
1.5.1 minor
1.4.1 patch
1.4.0 minor
1.3.5 patch
1.3.4 patch
1.3.3 minor
1.2.0 minor
1.1.0 major
0.1.1 patch
0.1.0 initial