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

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

overview / pkg / ggml / sources / llama.cpp / commit

author	Ruben Ortlam <redacted>
	Mon, 13 Apr 2026 12:21:31 +0000 (14:21 +0200)
committer	GitHub <redacted>
	Mon, 13 Apr 2026 12:21:31 +0000 (14:21 +0200)
commit	75f3bc94e649616162981c322e8e6b88ca5491e8
tree	d0da09c14c1ddfb262b1c414e160ac9a38671af2	tree
parent	aa00911d12198f1772905c319c0a073f87984883	commit \| diff

vulkan: Flash Attention DP4A shader for quantized KV cache (#20797)

* use integer dot product for quantized KV flash attention

* small improvements

* fix SHMEM_STAGING indexing

* add missing KV type quants

* fixes

* add supported quants to FA tests

* readd fast paths for <8bit quants

* fix mmq gate and shmem checks

Packaging of ggml-org/llama.cpp

RSS Atom

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