FreeScale reduces computational bubbles by up to 90.3% in distributed training of sequence recommendation models on 256 H100 GPUs via load balancing, prioritized embedding overlap, and SM-Free communication.
ISBN 978-1-939133-08-3
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.LG 2representative citing papers
citing papers explorer
-
FreeScale: Distributed Training for Sequence Recommendation Models with Minimal Scaling Cost
FreeScale reduces computational bubbles by up to 90.3% in distributed training of sequence recommendation models on 256 H100 GPUs via load balancing, prioritized embedding overlap, and SM-Free communication.
- ShuffleGate: Scalable Feature Optimization for Recommender Systems via Batch-wise Sensitivity Learning