]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 5b2c04f)
whisper : use vulkan as gpu backend when available (whisper/2302)
authorMatt Stephenson <redacted>
Tue, 16 Jul 2024 07:21:09 +0000 (03:21 -0400)
committerGeorgi Gerganov <redacted>
Fri, 9 Aug 2024 07:03:44 +0000 (10:03 +0300)
commit70c0ea35609a2ab87a358e25f4ffad1aad408992
treebe1a50b4d823c5b11371ed724132a697711a3a6dtree
parent5b2c04f4925e152c362b824f4b41eb2a081fa623commit | diff
whisper : use vulkan as gpu backend when available (whisper/2302)

* ggml: use vulkan as gpu backend when available

Signed-off-by: Matt Stephenson <redacted>
* whisper: enable using vk as default buffer type

Signed-off-by: Matt Stephenson <redacted>
---------

Signed-off-by: Matt Stephenson <redacted>
ggml/src/ggml-vulkan.cpp diff | blob | history
Packaging of ggml-org/llama.cpp