Mustafa Abduljabbar 82afb2bcfe Expose production tuning table in topo_explorer using internal RCCL/NCCL logic (#1628) ...

* Internal RCCL/NCCL functionality exposed when RCCL_EXPOSE_STATIC is enabled
* Algo/protocol/max channels can be obtained with the new RCCL API
* Introduce rccl_static and rccl_static_inline macros to work around invisible functions in core source files like enqueue.cc
* Add usage example in topo-explorer tool

2025-04-23 15:44:56 -04:00

..

EmptyKernelTest

adding cuda support for EmptyKernelTest (#913)

2023-10-11 14:11:12 -05:00

GraphBench

Graph unit tests (#656)

2022-12-01 10:28:42 -07:00

HelloRccl

Removing the experimental clique kernel files (#1610)

2025-03-20 18:10:01 -06:00

ib-test

Enable fp8 support (#1101)

2024-03-08 15:17:53 -08:00

JitterBench

removed gfx940 and gfx941 (#1606)

2025-03-20 09:34:53 -06:00

msccl-algorithms

single-node AR msccl algorithm tuning for MI300 (#1629)

2025-04-10 10:42:28 -04:00

msccl-unit-test-algorithms

MSCCL: Improve executor and integrate scheduler (#694)

2023-03-14 14:34:25 -07:00

p2p-latency-test

removed gfx940 and gfx941 (#1606)

2025-03-20 09:34:53 -06:00

rccl-prim-test

removed gfx940 and gfx941 (#1606)

2025-03-20 09:34:53 -06:00

RcclReplayer

reverting change to RcclReplayer (#1657)

2025-04-23 15:36:46 -04:00

scripts

added copyright (#1635)

2025-04-14 09:46:18 -05:00

time-trace

Disable Colltrace for --fast option (#778)

2023-06-21 14:16:09 -06:00

topo_expl

Expose production tuning table in topo_explorer using internal RCCL/NCCL logic (#1628)

2025-04-23 15:44:56 -04:00

TopoVisual

Replaced ROCmSoftwarePlatform and RadeonOpenCompute links with ROCm links. (#1125)

2024-03-25 16:29:13 -06:00

TransferBench

Replaced ROCmSoftwarePlatform and RadeonOpenCompute links with ROCm links. (#1125)

2024-03-25 16:29:13 -06:00