whisper.cpp
Reduce memory usage during Whisper inference
#431
Merged

Reduce memory usage during Whisper inference #431

ggerganov merged 15 commits into master from mem
ggerganov
ggerganov ggerganov force pushed from dadead51 to 34b8afe6 2 years ago
ggerganov ggerganov force pushed from 50692634 to f1b9913b 2 years ago
ggerganov ggerganov force pushed from 1f7cd041 to 60d0f9da 2 years ago
ggerganov ggerganov marked this pull request as ready for review 2 years ago
ggerganov ggerganov force pushed from b0c2268f to 41f31719 2 years ago
ggerganov ggml : add "scratch" buffer support
60eff46b
ggerganov ggml : support for scratch ring-buffer
0eea547a
ggerganov ggml : bug fix in ggml_repeat()
18210579
ggerganov ggml : error on scratch buffer overflow
0ba91b54
ggerganov whisper : use scratch buffers during inference (base model only)
1a1dee46
ggerganov whisper : update memory usage for all models
6cae05bd
ggerganov whisper : fix encoder memory usage
79148a21
ggerganov whisper : use whisper_context functions instead of macros
42d7dee4
ggerganov whisper : fix FF + remove it from README
4e0e2520
ggerganov ggml : reuse ggml_new_i32
d922aa4a
ggerganov ggml : refactor the scratch buffer storage
62205aed
ggerganov whisper : reorder scratch buffers in the decoder
01669ee8
ggerganov main : add option to disable temp fallback
bdf21fa6
ggerganov Update README.md
6ed13449
ggerganov ggerganov force pushed from 41f31719 to 6ed13449 2 years ago
ggerganov js : update whisper.js
a26f3a71
ggerganov ggerganov merged f3ee4a96 into master 2 years ago
ggerganov ggerganov deleted the mem branch 2 years ago
FELIXrobust
FELIXrobust approved these changes on 2024-07-01

Login to write a write a comment.

Login via GitHub

Reviewers
Assignees
No one assigned
Labels
Milestone