]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 073bb2c)
CUDA: skip compilation of superfluous FA kernels (#21768)
authorJohannes Gäßler <redacted>
Sat, 11 Apr 2026 16:52:11 +0000 (18:52 +0200)
committerGitHub <redacted>
Sat, 11 Apr 2026 16:52:11 +0000 (18:52 +0200)
commitff5ef8278615a2462b79b50abdf3cc95cfb31c6f
tree751e872a6084a0f622be79961e6bce0f79b4334atree
parent073bb2c20b5b2c919469653214aaa1a9895816a2commit | diff
CUDA: skip compilation of superfluous FA kernels (#21768)
ggml/src/ggml-cuda/fattn.cu diff | blob | history
Packaging of ggml-org/llama.cpp