mberenjk cca5172260 Upcast FP8 to Half (FP16) for Sum Operation (#1775) ...

* adding hadd and hadd2 support using builtin functions.

---------

Co-authored-by: Marzieh Berenjkoub <mberenjk@amd.com>

[ROCm/rccl commit: c84ee3d298]

2025-07-29 11:33:06 -05:00

..

rccl

Upcast FP8 to Half (FP16) for Sum Operation (#1775)

2025-07-29 11:33:06 -05:00