Pretrain, finetune ANY AI model of ANY size on 1 or 10,000+ GPUs with zero code changes.
Fix `save_hyperparameters` ignore precedence in subclasses (#21490)
A
Aditya Khedekar committed
14a3902aaf5c5f6bb90606e526495d6e5e25892b
Parent: a25515e
Committed by GitHub <noreply@github.com>
on 1/28/2026, 8:16:59 AM