mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2025-08-26 10:09:41 -04:00
* 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