Georgi Gerganov
|
2e59dced12
|
whisper : rename binaries + fix install (#2648)
* whisper : rename binaries + fix install
* cont : try to fix ci
* cont : fix emscripten builds
|
2024-12-21 09:43:49 +02:00 |
|
Georgi Gerganov
|
ed733e85a1
|
scripts : update to new build system
|
2024-12-09 11:30:16 +02:00 |
|
Georgi Gerganov
|
55e422109b
|
scripts : add turbo-q8_0 to the benchmark
|
2024-10-29 19:37:24 +02:00 |
|
Georgi Gerganov
|
8a35b58c4f
|
scripts : bench v3-turbo
|
2024-10-05 16:22:53 +03:00 |
|
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
|
52ccd4a3a8
|
files : rename ./extra to ./scripts
|
2024-04-09 20:13:41 +03:00 |
|