mirror of
https://github.com/ggml-org/whisper.cpp.git
synced 2026-07-31 23:20:48 -05:00
Huge performance improvement in the Encode (almost x2 on MacBook M1 Pro) Also various extra optimizations: - Multi-threaded NORM operator - Faster GELU via F16 cast
12 KiB
12 KiB