whisper.cpp
7094ea5e - whisper : use flash attention (#2152)

Commit
1 year ago
whisper : use flash attention (#2152) * whisper : use flash attention in the encoder * whisper : add kv_pad * whisper : remove extra backend instance (huh?) * whisper : use FA for cross-attention * whisper : use FA for self-attention * whisper : simplify encoder FA * whisper : add flash_attn runtime parameter * scripts : add bench log * scripts : add M1 Pro bench log
Author
Parents
Loading