ggml-org/llama.cpp b10405

on GitHub

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