]> git.djapps.eu Git - pkg/ggml/sources/llama.cpp/commit
overview / pkg / ggml / sources / llama.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: de21927)
vulkan: fuse adds (#15252)
authorJeff Bolz <redacted>
Sat, 16 Aug 2025 16:48:22 +0000 (11:48 -0500)
committerGitHub <redacted>
Sat, 16 Aug 2025 16:48:22 +0000 (11:48 -0500)
commit1fe00296f587dfca0957e006d146f5875b61e43d
tree3eb601367c74453729605aaa8734cbf80676de36tree
parentde2192794f4e8e04f2e8167ef2424905145e88fccommit | diff
vulkan: fuse adds (#15252)

* vulkan: fuse adds

Fuse adds that have the same shape, which are common in MoE models.
It will currently fuse up to 6 adds, because we assume no more than
8 descriptors per dispatch. But this could be changed.

* check runtimeDescriptorArray feature

* disable multi_add for Intel due to likely driver bug
ggml/src/ggml-vulkan/ggml-vulkan.cpp diff | blob | history
ggml/src/ggml-vulkan/vulkan-shaders/generic_binary_head.comp diff | blob | history
ggml/src/ggml-vulkan/vulkan-shaders/multi_add.comp [new file with mode: 0644] blob
ggml/src/ggml-vulkan/vulkan-shaders/utils.comp [new file with mode: 0644] blob
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp diff | blob | history
tests/test-backend-ops.cpp diff | blob | history
Packaging of ggml-org/llama.cpp