SOURCE-LINKED INTELLIGENCE

Online Draft Co-Training for Speculative Decoding in Large-Scale, Long-Context RL Post-Training

arXiv · AI, language, vision and robotics · article · Sep 7, 2026 · UTC

Speculative decoding accelerates rollout generation, which dominates the cost of reinforcement learning (RL) post-training. Online co-training can further increase the draft's accuracy, yielding greater speedups. However, scaling this approach to co-training on large models with long contexts poses two obstacles: (1) branch attention is unsupported by standard causal context-parallel (CP) implementations, and (2) target features span across pipeline-parallel (PP) stages. We address both with an end-to-end system for large-scale online draft co-training. For CP, we extend packed, load-balanced

Read original source ↗ Open in workspace

recordType

paper

region

Global