2 citations · 2 across the 4 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Silent Inconsistency in Data-Parallel Full Fine-Tuning: Diagnosing Worker-Level Optimization Misalignment
Hong Li, Zhen Zhou, Honggang Zhang +4
Data-parallel (DP) training with synchronous all-reduce is a dominant paradigm for full-parameter fine-tuning of large language models (LLMs). While parameter synchronization guara…
cs.LG2024★ 2 cited
Enhancing Performance and Scalability of Large-Scale Recommendation Systems with Jagged Flash Attention
Rengan Xu, Junjie Yang, Yifan Xu +17
The integration of hardware accelerators has significantly advanced the capabilities of modern recommendation systems, enabling the exploration of complex ranking paradigms previou…