Metraipolis › archive › dc_8414666cd51d
WeightBridge: An Efficient Weight Transfer Library for Reinforcement Learning — arXiv:2609.25442
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.25442
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T14:37:20.152Z
- SHA-256 of the archived text
1ec0174553e98e1052a0c5c114d0f24f21ab151387e4bba3021c7a3a14e1c333- Stable URL of this page
https://metraipolis.com/documento/dc_8414666cd51d
How to cite
WeightBridge: An Efficient Weight Transfer Library for Reinforcement Learning — arXiv:2609.25442 — arXiv (en), https://arxiv.org/abs/2609.25442 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8414666cd51d (Metraipolis archive dc_8414666cd51d, sha256 1ec0174553e98e1052a0c5c114d0f24f21ab151387e4bba3021c7a3a14e1c333)
BibTeX
@misc{dc8414666cd51d,
title = {WeightBridge: An Efficient Weight Transfer Library for Reinforcement Learning — arXiv:2609.25442},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.25442},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8414666cd51d; sha256 1ec0174553e98e1052a0c5c114d0f24f21ab151387e4bba3021c7a3a14e1c333},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.25442. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Weight transfer - the propagation of updated parameters from trainers to rollout generators - is becoming an important performance bottleneck in reinforcement learning (RL) systems for LLMs. The central challenge is supporting the diverse trainer and rollout layouts and synchronization requirements of modern RL workloads without sacrificing efficiency. Existing solutions are efficient under some configurations but perform poorly or lack support under others. We present WeightBridge, a flexible, efficient weight-transfer library designed to deliver high performance across diverse RL configurations. WeightBridge first automatically extracts the correspondence between trainer and rollout weight layouts, then plans and executes redundancy-free and load-balanced weight transfer. It exposes a small, general API while coordinating workers across diverse synchronization modes. Across configurations spanning different models, parallelization layouts, and synchronization modes, WeightBridge reduces average GPU stall time by up to 42$\times$ over the state-of-the-art open-source RL framework and achieves high performance in all settings. A coding agent was able to integrate WeightBridge into two different RL frameworks without manual guidance, demonstrating the generality and ease of use of its APIs. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-23 in cs.DC). Categorie arXiv: Distributed, Parallel, and Cluster Computing (cs.DC) ; Machine Learning (cs.LG); Networking and Internet Architecture (cs.NI). Pagina del lavoro: https://arxiv.org/abs/2609.25442 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T13:47:35.185Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).