Kawrakow 2fddc45a02 Vulkan: flash attention for DeepSeek models (#584) ...

* vulkan: support mixed/deepseekR1 FA head sizes (#14509)

* vulkan: better parameterize FA by head sizes

* vulkan: support mixed/deepseekR1 FA head sizes

* Fix the FA cherry-pick

---------

Co-authored-by: Jeff Bolz <jbolz@nvidia.com>
Co-authored-by: Iwan Kawrakow <iwan.kawrakow@gmail.com>

2025-07-05 15:14:12 +02:00

..

cmake

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

include

Chnage KQ mask padding to 64 (#574)

2025-07-03 10:43:27 +02:00

src

Vulkan: flash attention for DeepSeek models (#584)

2025-07-05 15:14:12 +02:00

.gitignore

Merge mainline llama.cpp (#3)

2024-07-27 07:55:01 +02:00

CMakeLists.txt

Merge vulkan code from mainline up to commit of 6/28/2025 (#563)

2025-07-02 08:49:42 +02:00