Nusrat Islam 3fbafef948 ext-src: tuning for allreduce8 kernel (#1560) ...

This PR tunes the number of threadblocks used for larger (>1MB)
message sizes.

[ROCm/rccl commit: fdf75fd2c1]

2025-02-21 19:34:38 -06:00

..

scripts

Merge remote-tracking branch 'nccl/master' into develop

2025-01-23 12:08:46 -06:00

CheckSymbolExistsNoWarn.cmake

Hide or fix all build warnings (#1331)

2024-11-04 09:46:42 -07:00

Dependencies.cmake

Add unique files to source list (#1144)

2024-04-15 09:46:53 -06:00

DownloadProject.cmake

Only initialize MSCCL++ when runtime-enabled. (#1266)

2024-07-22 00:41:31 -06:00

DownloadProject.CMakeLists.cmake.in

Download GTest if not found in system (#237)

2020-08-06 09:36:58 -06:00

FindIBVerbs.cmake

Integrated RCCL with MSCCL++ for small message sizes (#1231)

2024-07-12 15:32:58 -06:00

Findmscclpp_nccl.cmake

Integrated RCCL with MSCCL++ for small message sizes (#1231)

2024-07-12 15:32:58 -06:00

MSCCLPP.cmake

ext-src: tuning for allreduce8 kernel (#1560)

2025-02-21 19:34:38 -06:00