git.djapps.eu Git - pkg/ggml/sources/ggml/commit

]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit

overview / pkg / ggml / sources / ggml / commit

author	Jeff Bolz <redacted>
	Thu, 5 Feb 2026 15:26:38 +0000 (09:26 -0600)
committer	Georgi Gerganov <redacted>
	Sat, 7 Feb 2026 08:37:38 +0000 (10:37 +0200)
commit	8ab9ddbf6b051daaf8d6cf248c98b4c2d14316eb
tree	43830d9187bb6ca19ea7eaeb0cf43bd73dfeb6c9	tree
parent	51f911d35c8d04ca5a98575dc56c488fc12dfaec	commit \| diff

vulkan: Preprocess FA mask to detect all-neg-inf and all-zero. (llama/19281)

Write out a 2-bit code per block and avoid loading the mask when it
matches these two common cases.

Apply this optimization when the mask is relatively large (i.e. prompt
processing).

Packaging of ggml-org/ggml

RSS Atom

src/ggml-vulkan/ggml-vulkan.cpp		diff \| blob \| history
src/ggml-vulkan/vulkan-shaders/flash_attn.comp		diff \| blob \| history
src/ggml-vulkan/vulkan-shaders/flash_attn_base.glsl		diff \| blob \| history
src/ggml-vulkan/vulkan-shaders/flash_attn_cm1.comp		diff \| blob \| history
src/ggml-vulkan/vulkan-shaders/flash_attn_cm2.comp		diff \| blob \| history
src/ggml-vulkan/vulkan-shaders/flash_attn_mask_opt.comp	[new file with mode: 0644]	blob
src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp		diff \| blob \| history
tests/test-backend-ops.cpp		diff \| blob \| history