mirror of
https://github.com/ggml-org/llama.cpp.git
synced 2026-07-21 18:25:57 +00:00
* vulkan/cpu: Support f16 as SET_ROWS src. This adds full support for f16 SET_ROWS (equivalent to f32) to vulkan and CPU backends, and adds more backend tests. * Set DenormPreserve 16 when supported, to try to fix failures on Intel * tune error threshold * update metal supports_op