llama.cpp

d48e8764 - ggml-cuda: add mem check for fusion (#19916)

ggml-cuda: add mem check for fusion (#19916) * ggml-cuda: add mem check for fusion * Replace NaNs with -FLT_MAX * fix typo Co-authored-by: Johannes Gäßler <johannesg@5d6.de> --------- Co-authored-by: Johannes Gäßler <johannesg@5d6.de>