]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
vulkan: add `v_dot2_f32_f16` support in matrix-matrix multiplication and Flash Attent...
authorRuben Ortlam <redacted>
Tue, 9 Jun 2026 11:27:04 +0000 (13:27 +0200)
committerGeorgi Gerganov <redacted>
Mon, 15 Jun 2026 07:33:53 +0000 (10:33 +0300)
commit686bc802d1f5df3cf4a23102eca785b62877619b
treeeb7054c7ec55fcbe13b7b4f28528d7197e3311e7
parent28c7ed3db7e24261742123d6b33a90b0ef681808
vulkan: add `v_dot2_f32_f16` support in matrix-matrix multiplication and Flash Attention (llama/24123)

* vulkan: add support for valve fp16 dot2 extension

* use macro for dot2 path choice

* properly check for the feature

* add dot_product abstraction to reduce preprocessor branching
ggml/src/ggml-vulkan/ggml-vulkan.cpp
ggml/src/ggml-vulkan/vulkan-shaders/dot_product_funcs.glsl [new file with mode: 0644]
ggml/src/ggml-vulkan/vulkan-shaders/flash_attn.comp
ggml/src/ggml-vulkan/vulkan-shaders/mul_mm.comp
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp