💾 trunk/c3c33fd3481ab28ef0037bbd9b72588fbdfec691: [CUDA][NCCL] Fix nccl.broadcast dropping the root argument (#187216)
Nachrichtenbereich: 💾 Downloads
🔗 Quelle: github.com
Fixes #179908
Summary
torch.cuda.nccl.broadcast(tensors, root=N) silently ignores root and always broadcasts from tensors[0], while nccl.reduce honors root — full root-cause chain in my issue... [Weiterlesen]