SOURCE-LINKED INTELLIGENCE

vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation

arXiv · AI, language, vision and robotics · article · Sep 21, 2026 · UTC

Deploying language-conditioned manipulation without a dedicated GPU requires efficient inference and action chunks that cover the delay between policy queries. We present vla.simd, a CPU inference engine that combines shared SIMD micro-kernels, reusable computation, and target-specific optimization. We relate query latency and execution horizon to action availability under lagged and time-aligned execution, distinguishing action supply from feedback frequency. Across six policies and four CPUs, vla.simd achieves approximately $1.4\times$ median speedup over compiled PyTorch references while pr

Read original source ↗ Open in workspace

recordType

paper

region

Global