כתבה
arXiv cs.AI ·
WAMJET: כלי להאצת מודלים
WAMJET: A Harness for World Action Model Acceleration
WAMJET הוא כלי להאצת מודלים של World Action Models. הוא משתמש בסוכנים קודים כדי לשפר ביצועים. WAMJET מאפשר האצה של עד 9.95x בלי איבוד נתונים.
תקציר מקורי באנגליתarXiv:2610.03797v3 Announce Type: replace-cross Abstract: World Action Models (WAMs) leverage pretrained video foundation models for robot manipulation, but their large backbones and video-action co-prediction are expensive. Although existing acceleration techniques offer many ways to reduce this cost, selecting and composing them requires substantial engineering for each model and hardware platform. To tackle this bottleneck, we present WAMJET, an agentic harness that accelerates WAM inference by equipping coding agents with reusable optimization guidance and measurement and validation tools. WAMJET follows a bottleneck-driven workflow where the agent profiles inference, modifies targeted code, validates effects, and iteratively refines the acceleration stack as bottlenecks shift, while p
קרא במקור המקורי
arxiv.org
פתח כתבה מקורית