whisper.cpp/ggml
Jeff Bolz d4c391bb19
vulkan/cpu: Support f16 as SET_ROWS src. (llama/25432)
* 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
2026-07-30 16:31:39 +03:00
..
cmake ggml : Parallelize quant LUT init (llama/23595) 2026-05-25 12:26:07 +03:00
include ggml : add a set of functions for checking contiguity of inner tensor dimensions (llama/25650) 2026-07-30 16:31:39 +03:00
src vulkan/cpu: Support f16 as SET_ROWS src. (llama/25432) 2026-07-30 16:31:39 +03:00
.gitignore
CMakeLists.txt ggml-et: Initial ET backend (llama/24179) 2026-07-30 16:31:36 +03:00