]> git.djapps.eu Git - pkg/ggml/sources/whisper.cpp/commit
overview / pkg / ggml / sources / whisper.cpp / commit
summary | shortlog | log | commit | commitdiff | tree
(parent: 782f122)
vulkan: Use cm2 decode_vector for mul_mat_id B matrix loads (llama/23991)
authorJeff Bolz <redacted>
Mon, 8 Jun 2026 08:40:37 +0000 (03:40 -0500)
committerGeorgi Gerganov <redacted>
Mon, 15 Jun 2026 07:33:53 +0000 (10:33 +0300)
commitfbf720dc9f3570ed98bd5e43806fbc4a53428084
treec5e4cbbd8eb5f80d7dd5f0074cba8b3523473d7etree
parent782f1226c8d9c49a6c64d654bacfe15531913a6ccommit | diff
vulkan: Use cm2 decode_vector for mul_mat_id B matrix loads (llama/23991)

This allows vec4 loads of the B elements. Also increase BK to 64 when this is
enabled. Neither of these alone is consistently faster, but together these give
a nice speedup.

In ggml-vulkan.cpp, we need to make sure the B matrix alignment and stride are
multiples of 4.
ggml/src/ggml-vulkan/ggml-vulkan.cpp diff | blob | history
ggml/src/ggml-vulkan/vulkan-shaders/mul_mm_cm2.comp diff | blob | history
ggml/src/ggml-vulkan/vulkan-shaders/vulkan-shaders-gen.cpp diff | blob | history
Packaging of ggerganov/whisper.cpp