michael-a-kuykendall/shimmy
steady⚡ Pure-Rust WebGPU inference engine — OpenAI-API compatible, GGUF native, runs on any GPU. No Python. No llama.cpp. Single binary.
Rust
View on GitHub
Stars
5,908
Forks
577
Open issues
11
24h
+3
+0.1%
7d
+41
+0.7%
Refresh
1h
Star history (7 days)
Last checked
31m ago
Last pushed
31 Aug 2026
Next check
just now