Abstract
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 preserving fp32 numerical fidelity. We also introduce IMPACT, an ACT-based policy with cached text representations and language-modulated visual features. IMPACT is the only language-conditioned policy in our evaluated set that supplies at least 30 actions/s on the Raspberry Pi 5: after a 90 s thermal soak, it supplies 33.5 actions/s in fp32 and 81.2 with int8. Separate GPU evaluations yield $76.4\%$ mean success across four LIBERO suites without robot pretraining; instruction-shuffling tests demonstrate selection among familiar goals. Trials with IMPACT on an SO-101 arm and SmolVLA on a UR10e with a Robotiq gripper demonstrate CPU deployment on two robot embodiments.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Nguyen, K. D., Truong, H. M., & Le, A. T. (2026). vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation. https://omanscience.com/en/articles/vla-simd-efficient-cpu-inference-for-language-conditioned-manipulation
MLA 9
Nguyen, Khanh D., et al. "vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation." https://omanscience.com/en/articles/vla-simd-efficient-cpu-inference-for-language-conditioned-manipulation.
Chicago (author–date)
Nguyen, Khanh D., Hoang M. Truong, and An T. Le. 2026. "vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation." https://omanscience.com/en/articles/vla-simd-efficient-cpu-inference-for-language-conditioned-manipulation.
Harvard
Nguyen, K. D., Truong, H. M. and Le, A. T. (2026) 'vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation', Available at: https://omanscience.com/en/articles/vla-simd-efficient-cpu-inference-for-language-conditioned-manipulation.
Vancouver
Nguyen KD, Truong HM, Le AT. vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation. https://omanscience.com/en/articles/vla-simd-efficient-cpu-inference-for-language-conditioned-manipulation
IEEE
K. D. Nguyen, H. M. Truong, and A. T. Le, "vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation," https://omanscience.com/en/articles/vla-simd-efficient-cpu-inference-for-language-conditioned-manipulation.