Jim Wu e79e4bf660 ggml-hip : remove -funsafe-math-optimizations (#26696) ...

It enables -fassociative-math, which reassociates FP reductions and can flip
greedy argmax on RDNA3.5 (e.g. MTP speculative decode diverging from the
non-speculative baseline). Drop it so HIP builds are IEEE-conformant.

Co-authored-by: Jim Wu <ywu@xilinx.com>

2026-08-13 08:38:02 +02:00

..

cmake

cmake : add config version support (ggml/1582)

2026-08-12 14:23:43 +03:00

include

llama: add default load-mode auto, which avoids mmap on iGPUs (#26081)

2026-08-11 09:20:46 +03:00

src

ggml-hip : remove -funsafe-math-optimizations (#26696)

2026-08-13 08:38:02 +02:00

.gitignore

vulkan : cmake integration (#8119)

2024-07-13 18:12:39 +02:00

CMakeLists.txt

cmake : add config version support (ggml/1582)

2026-08-12 14:23:43 +03:00