]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 554fd57)
CUDA: Changing the CUDA scheduling strategy to spin (#16585)
authorJulius Tischbein <redacted>
Wed, 15 Oct 2025 11:54:15 +0000 (13:54 +0200)
committerGitHub <redacted>
Wed, 15 Oct 2025 11:54:15 +0000 (14:54 +0300)
commit5acd455460f457942d8dd02e3dd9b1eebfce99fe
tree64c9f7022058bba98fc799e92ad9545f87822934tree
parent554fd578a5ed78a10f371f5850c6a69aa83df15acommit | diff
CUDA: Changing the CUDA scheduling strategy to spin (#16585)

* CUDA set scheduling strategy to spinning for cc121

* Using prop.major and prop.minor, include HIP and MUSA

* Exclude HIP and MUSA

* Remove trailing whitespace

Co-authored-by: Johannes Gäßler <redacted>
* Remove empty line

Co-authored-by: Johannes Gäßler <redacted>
---------

Co-authored-by: Johannes Gäßler <redacted>
ggml/src/ggml-cuda/ggml-cuda.cu diff | blob | history
Packaging of ggml-org/llama.cpp