Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
fix: port already in use & nccl errors in gpu tests (#21335)
* update * update with correct link * Apply suggestion from @deependujha * Revert "Fix EADDRINUSE errors in distributed tests with port manager and retr…" This reverts commit 6a8d94380e5b5e2b116b7e1e7edd23c57f42082f. * claymore --------- Co-authored-by: Bhimraj Yadav <bhimrajyadav977@gmail.com>
D
Deependu committed
c913649a1b0049491206032c5d3f88e8b18f94b6
Parent: 19912d0
Committed by GitHub <noreply@github.com>
on 11/6/2025, 8:15:22 AM