Georgi Gerganov
f3ee4a9673
whisper : reduce memory usage during inference (#431)
* ggml : add "scratch" buffer support
* ggml : support for scratch ring-buffer
* ggml : bug fix in ggml_repeat()
* ggml : error on scratch buffer overflow
* whisper : use scratch buffers during inference (base model only)
* whisper : update memory usage for all models
* whisper : fix encoder memory usage
* whisper : use whisper_context functions instead of macros
* whisper : fix FF + remove it from README
* ggml : reuse ggml_new_i32
* ggml : refactor the scratch buffer storage
* whisper : reorder scratch buffers in the decoder
* main : add option to disable temp fallback
* Update README.md
2023-02-04 09:45:52 +02:00
..
2023-02-04 09:10:25 +02:00
2023-01-18 21:19:50 +02:00
2023-01-15 11:34:03 +02:00
2023-01-15 11:29:57 +02:00
2023-01-08 13:03:33 +02:00
2023-02-04 09:45:52 +02:00
2023-01-18 21:22:52 +02:00
2023-01-15 11:29:57 +02:00
2023-01-08 13:03:33 +02:00
2023-01-08 13:03:33 +02:00
2023-01-16 21:57:35 +02:00
2022-11-04 22:26:08 +02:00
2023-01-08 13:03:33 +02:00
2023-01-15 14:08:12 +02:00
2023-01-23 20:49:00 +02:00
2023-02-04 09:10:25 +02:00
2022-10-25 20:53:48 +03:00
2022-11-26 10:22:42 +02:00
2023-02-04 08:49:15 +02:00
2023-01-27 01:13:31 +02:00
2022-12-08 19:20:04 +02:00
2022-12-07 22:12:08 +02:00