Files
rocm-systems/projects/rccl/cmake/scripts
mberenjk c76a4492f1 Added useAcc as a template parameter to address the performance regression (#1856)
* Added useAcc as a template parameter to address the 2% performance regression in allreduceWithBias
---------

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


[ROCm/rccl commit: c61152baa4]
2025-08-14 15:58:54 -05:00
..
2024-02-12 17:56:15 -07:00