mirror of
https://github.com/microsoft/mscclpp.git
synced 2026-07-15 03:40:14 +00:00
Resolve the FP8 conversion conflict by using direct float2-to-E4M3 conversion on all CUDA architectures while preserving the MSCCL++ packed vector storage path. Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com> Copilot-Session: efbacae6-f679-430b-bc16-b45ae162fc76