Metraipolis › archive › dc_2aa162cd5e8d

vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation — arXiv:2609.24274

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.24274
License (as archived): CC0-1.0
Archived: 2026-10-09T22:24:19.769Z
SHA-256 of the archived text: fa7de8dee2293f656daf540a308257697ee7f677135977df59c8362322b8b477
Stable URL of this page: https://metraipolis.com/documento/dc_2aa162cd5e8d

How to cite

vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation — arXiv:2609.24274 — arXiv (en), https://arxiv.org/abs/2609.24274 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2aa162cd5e8d (Metraipolis archive dc_2aa162cd5e8d, sha256 fa7de8dee2293f656daf540a308257697ee7f677135977df59c8362322b8b477)

BibTeX

@misc{dc2aa162cd5e8d,
  title = {vla.simd: Efficient CPU Inference for Language-Conditioned Manipulation — arXiv:2609.24274},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.24274},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2aa162cd5e8d; sha256 fa7de8dee2293f656daf540a308257697ee7f677135977df59c8362322b8b477},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24274. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Deploying language-conditioned manipulation without a dedicated GPU requires efficient inference and action chunks that cover the delay between policy queries. We present this http URL , 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, this http URL 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.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.RO).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Systems and Control (eess.SY).
Pagina del lavoro: https://arxiv.org/abs/2609.24274 — 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 2026-10-09T21:59:59.703Z dalla pagina https://arxiv.org/catchup/cs.RO/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).