]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
overview / pkg / ggml / sources / whisper.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: d14e626)
vulkan: fuse adds (llama/15252)
authorJeff Bolz <redacted>
Sat, 16 Aug 2025 16:48:22 +0000 (11:48 -0500)
committerGeorgi Gerganov <redacted>
Mon, 18 Aug 2025 17:30:45 +0000 (20:30 +0300)
commitc44d4496353040236a60f6f9c5ae807cbc6f14f4
tree32e3759fbf135d672241babd35354cec2233dd4ftree
parentd14e626e6a4f1623b50f625a0628eb8c76296556commit | diff
vulkan: fuse adds (llama/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
Packaging of ggerganov/whisper.cpp