]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
overview / pkg / ggml / sources / whisper.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: aaf3f39)
metal: use shared buffers on eGPU (llama/17866)
authorJeremy Demeule <redacted>
Mon, 15 Dec 2025 14:14:49 +0000 (15:14 +0100)
committerGeorgi Gerganov <redacted>
Thu, 18 Dec 2025 06:20:56 +0000 (08:20 +0200)
commitb90ec07abad518034e503279982107d9fca26df1
treee07d187afc96adb051defcb5d88788c0ec07172btree
parentaaf3f39b4abaeeb3c60fb0ad565e2d38a032629fcommit | diff
metal: use shared buffers on eGPU (llama/17866)

* metal: use shared buffers on eGPU

With #15906, I noticed on important regression when using metal backend on eGPU.
This commit restore the previous behavior and add an option to force its activation.

* metal: use shared buffers on eGPU

* metal: use shared buffers on eGPU
ggml/src/ggml-metal/ggml-metal-device.m diff | blob | history
Packaging of ggerganov/whisper.cpp