works on
eager execution 1large language model training 1memory optimization 1online profiling 1swap-based management 1

From the 1 of 3 linked papers with an AI index.

collaborators
Showing cs.DCShow all

1 paper · 1 filter

cs.DC2026

SmartSwap: Swap-Based Memory Optimization for LLM Training under Varying Operator Sequences

Zibo Wang, Yuhang Zhou, Zhibin Wang +13

The paper introduces SmartSwap, a swap‑based memory optimization framework that adapts to varying operator sequences in eager‑mode training of large language models, using a lightw…