]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
vulkan: Handle updated FA dim2/3 definition (llama/14518)
authorJeff Bolz <redacted>
Sat, 5 Jul 2025 07:26:04 +0000 (02:26 -0500)
committerGeorgi Gerganov <redacted>
Sat, 12 Jul 2025 13:05:00 +0000 (16:05 +0300)
commit26af18087718b78fb5d606047d6d760a4cd8bbaf
treefa41cf6aee64d1871550a2dcc5c574403f0ab4d5
parentdadec19060210ceeefd8184f6223a39dbb92835d
vulkan: Handle updated FA dim2/3 definition (llama/14518)

* vulkan: Handle updated FA dim2/3 definition

Pack mask boolean and n_head_log2 into a single dword to keep the push
constant block under the 128B limit.

* handle null mask for gqa

* allow gqa with dim3>1
src/ggml-vulkan/ggml-vulkan.cpp
src/ggml-vulkan/vulkan-shaders/flash_attn.comp
src/ggml-vulkan/vulkan-shaders/flash_attn_base.comp
src/ggml-vulkan/vulkan-shaders/flash_attn_cm1.comp
src/ggml-vulkan/vulkan-shaders/flash_attn_cm2.comp