← Back to all news
arXiv Machine Learning By Yibo Shen, Xudong Han, Xiaowei Zhu, Gen Li, Zhenxuan Pan

RoutePack: Replay-Guided Expert Placement and Rollout Trajectory Scheduling for MoE Reinforcement Learning

Read the original on arXiv Machine Learning →

RoutePack is a replay‑guided planner that coordinates expert placement and rollout‑trajectory scheduling for Mixture‑of‑Experts reinforcement learning models. By incrementally adjusting expert placement while preserving residency and then rescheduling trajectories into token‑capped micro‑batches, it jointly balances dense‑side work and layer‑wise expert peaks under fixed capacity constraints. Evaluations on 7.9B and 124B hybrid‑attention MoE models across NVIDIA H20‑3e configurations show throughput gains of 4.44‑11.85% over a DP‑local first‑fit‑decreasing baseline and 1.33‑5.28% over expert rerouting alone.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv Machine Learning
Aug 14

RoutePack: Expert Placement and Attention-Aware Data Packing for MoE Reinforcement Learning

arXiv:2608. 12146v1 Announce Type: cross Abstract: Training Mixture-of-Experts (MoE) models for reinforcement learning (RL) couples two load-balancing problems: sequence composition determines dense attention work in each data-parallel microbatch, while token routing determines sparse expert work on expert-parallel ranks.

By Yibo Shen, Xudong Han, Xiaowei Zhu, Gen Li, Zhenxuan Pan
reinforcement-learningefficiency
More like this →
Hugging Face Trending Papers
Aug 11

Scheduling Mixed RL Rollouts Beyond Prefix Locality

Modern reinforcement learning (RL) post-training pipelines for large language models (LLMs) increasingly combine rollout workloads across multiple domains and feedback paradigms. Prefix-aware routing improves inference efficiency through cache reuse and load balancing, but it does not control how heterogeneous rollout sessions compete for KV-cache capacity.

llmsagentsreinforcement-learningefficiency
More like this →
arXiv AI
Oct 7

Memory-Efficient Expert Routing for Distributed MoE Training

The paper introduces RelayMoE, a ring‑based execution model for Mixture‑of‑Experts (MoE) training that reduces memory usage by avoiding full top‑k expanded dispatch buffers. RelayMoE dynamically chooses between expert and token routing based on communication volume and overlaps data transfer with computation, enabling efficient backward recomputation. Experiments on 30B–57B MoE models show up to a 2× speedup over Megatron‑LM and a 2.02× throughput improvement while extending trainable sequence lengths by up to 2.85×.

By Arnab Kanti Tarafder, Jaume Guasch-Mart\'i, Gokcen Kestor, Jie Ren
efficiency
More like this →