8 Commits

Author	SHA1	Message	Date
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
Georgi Gerganov	f56b8305c4	sync : ggml	2024-05-14 19:16:32 +03:00
Georgi Gerganov	130f43e4b8	scripts : sync ggml-rpc	2024-05-14 19:15:35 +03:00
Georgi Gerganov	fe179ae0cc	sync : ggml	2024-05-13 11:02:26 +03:00
Georgi Gerganov	8f253ef3af	sync : ggml	2024-04-09 20:27:55 +03:00
Georgi Gerganov	c7dc37f97c	license : update copyright notice + add AUTHORS	2024-04-09 20:27:44 +03:00
Georgi Gerganov	3b8aade3c2	scripts : update sync	2024-04-09 20:25:50 +03:00
Georgi Gerganov	52ccd4a3a8	files : rename ./extra to ./scripts	2024-04-09 20:13:41 +03:00