Georgi Gerganov 7094ea5e75 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		2024-05-15 09:38:19 +03:00
..
CMakeLists.txt	wchess : whisper assisted chess (#1595)	2023-12-14 15:58:26 +02:00
wchess.cmd.cpp	whisper : use flash attention (#2152)	2024-05-15 09:38:19 +03:00