shipfeedAI news, curated daily

23:52:14 CET
20 MAY23:52:14shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

whisper.cpp v1.7.2-pre

whisper.cpp releases v1.7.2-pre with Metal backend improvements, reduced memory usage for large samples, and removal of the ggml_context limit, pending investigation of reported memory leaks.

Nov 15 · · primary fetch1 sourceupdated Nov 15 ·

Overview This is a pre-release since I think there have been some reports about memory leaks which I haven't had the time to investigate and confirm. If these are resolved in the next days, will add them to the official `1.7.2` release next week. Various improvements in the Metal backend Fix extra memory usage for large samples Remove limit for `ggml_context` (i.e. more beams and processors are supported) | CPU | Config | Model | Th | FA | Enc. | Dec. | Bch5 | PP | Commit | | --- | --- | --- | --- | --- | --- | --- | --- | --- | --- | | M2 Ultra | METAL | tiny | 1 | 1 | 9.51 | 1.39 | 0.41 | 0.01 | 83ac284 | | M2 Ultra | METAL | tiny-q5_0 | 1 | 1 | 9.57 | 1.41 | 0.42 | 0.01 | 83ac284 | | M2 Ultra | METAL | tiny-q5_1 | 1 | 1 | 8.74 | 1.39 | 0.42 | 0.01 | 83ac284 | | M2 Ultra | METAL | tiny-q8_0 | 1 | 1 | 8.36 | 1.33 | 0.41 | 0.01 | 83ac284 | | M2 Ultra | METAL | base | 1 | 1 | 14.27 | 1.90 | 0.63 | 0.02 | 83ac284 | | M2 Ultra | METAL | base-q5_0 | 1 | 1 | 15.50 | 1.90 | 0.65 | 0.02 | 83ac284 | | M2 Ultra | METAL | base-q5_1 | 1 | 1 | 15.67 | 1.88 | 0.65 | 0.02 | 83ac284 | | M2 Ultra | METAL | base-q8_0 | 1 | 1 | 14.69 | 1.81 | 0.63 | 0.02 | 83ac284 | | M2 Ultra | METAL | small | 1…

read full article on github.com
§ sources1 publication · timeline below
  1. github.comwhisper.cpp v1.7.2-preprimary