StaleFlow enforces per-trajectory staleness bounds and coordinates rollout data routing, achieving 1.42–2.68x higher RL post-training throughput with comparable convergence.
Galvatron: Efficient transformer training over multiple gpus using automatic parallelism.Proc
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.DC 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
StaleFlow: Staleness-Aware Data Management for Mitigating Data Skewness in Fully Disaggregated RL Post-Training
StaleFlow enforces per-trajectory staleness bounds and coordinates rollout data routing, achieving 1.42–2.68x higher RL post-training throughput with comparable convergence.