]> git.djapps.eu Git - pkg/ggml/sources/ggml/commit
vulkan: support mixed/deepseekR1 FA head sizes (llama/14509)
authorJeff Bolz <redacted>
Thu, 3 Jul 2025 18:21:14 +0000 (13:21 -0500)
committerGeorgi Gerganov <redacted>
Sat, 12 Jul 2025 13:05:00 +0000 (16:05 +0300)
commitb29924d2c37d2ad03940c06479bb4bbbef1125aa
tree21e48f6dc7bb2529d058c2355d82803323da2ae2
parent72be4c8ec634aae4f5ab8845bd5cc8c78fcfd04a
vulkan: support mixed/deepseekR1 FA head sizes (llama/14509)

* vulkan: better parameterize FA by head sizes

* vulkan: support mixed/deepseekR1 FA head sizes
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