]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
overview / pkg / ggml / sources / whisper.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: b7809c4)
llama: use FA + max. GPU layers by default (llama/15434)
authorJohannes Gäßler <redacted>
Sat, 30 Aug 2025 14:32:10 +0000 (16:32 +0200)
committerGeorgi Gerganov <redacted>
Sat, 20 Sep 2025 10:42:44 +0000 (13:42 +0300)
commitf6ba3949b6f83260a4ff5edf40e5016b3ecc0915
tree65acc71158d98941044a4b1e38f066a77c006debtree
parentb7809c401b06ef7fd59ef3d2ddb7e0554c7c87ebcommit | diff
llama: use FA + max. GPU layers by default (llama/15434)

* llama: use max. GPU layers by default, auto -fa

* ggml-backend: abort instead of segfault
ggml/src/ggml-backend.cpp diff | blob | history
Packaging of ggerganov/whisper.cpp