VLA推論時間はどこで消費されるのか?GPU間のボトルネックと最適化の相互作用
Where Is VLA Inference Time Spent? Bottlenecks and Optimization Interactions Across GPUs
7種類のVLAモデルと4世代のGPUで7系統の推論最適化手法を計測し、CPU起動オーバーヘッドやメモリ帯域、カーネル効率が最適化効果をどう左右するかを分析して、最適化を積み重ねる際の指針VLA-Triageを導出した論文。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Muhammad Danish Waseem, Ahmed Ali-Eldin Hassan
分類: cs.RO
原文アブストラクト
Vision-language-action (VLA) models map camera observations and language instructions to robot actions. However, their large backbones and repeated action generation can make inference take longer than the robot's real-time requirements for its next action. To reduce the load of VLA computations, researchers have proposed multiple optimization approaches, including quantization and pruning. These optimizations can be combined with other general optimizations such as better kernel compilation or using CUDA graphs instead of the eager mode. However, most of these optimization results are usually reported on a single GPU type, typically for a few VLA models, with no analysis of what the real bottlenecks are for a model on a particular hardware or how these optimizations would generalize beyond the reported results. In this paper, we provide a comprehensive measurement study of seven families of inference optimization methods, from CUDA graphs and compilation to token pruning and quantization, on seven state-of-the-art VLAs evaluated on four GPU families ranging from a datacenter H100 to an embedded Jetson Thor. We analyse how CPU launch overhead, memory bandwidth, and kernel efficiency jointly shape optimization gains, and how applying one method changes the benefit of another. From this analysis, we derive VLA-Triage, guidelines for stacking optimizations under latency budgets. The guidelines identify which stages can provide the required savings and which combinations need testing in the deployed execution mode.