Man Yuan
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Distributed×1
Frequent co-authors
Research Timeline
2026
Libra: Taming Attention Workload Skew in Long-Context LLM Training with Bounded Sequence Pool
Libra is a load balancing approach for long-context LLM training that groups packed sequences into fixed-size pools and reduces attention workload variance, improving end-to-end throughput and straggler-attention speedup.
Highlighted terms show continued research focus across papers
Papers
cs.DCEmpiricalRecentJul 25, 2026
Libra: Taming Attention Workload Skew in Long-Context LLM Training with Bounded Sequence Pool
Yan Wang, Xiulong Yuan, Kaiming Yang, Jiaxuan Peng +15 more
Libra is a load balancing approach for long-context LLM training that groups packed sequences into fixed-size pools and reduces attention workload variance, improving end-to-end throughput and straggl…
View →