Papers
arxiv:2606.08094

vla.cpp: A Unified Inference Runtime for Vision-Language-Action Models

Published on Jun 6
Authors:
,
,
,
,
,
,
,

Abstract

A portable C++ runtime enables efficient cross-hardware deployment of diverse vision-language-action policies by optimizing compute-bound inference and reducing memory usage.

Vision-Language-Action (VLA) policies are typically shipped as Python/PyTorch stacks that assume a workstation-class GPU, a mismatch for the hardware on which robots actually run. We present vla.cpp, a portable C++ inference runtime built on llama.cpp. To our knowledge, it is the first ggml-class engine to natively serve the flow-matching and diffusion VLA inference pattern, in which a cached vision-language prefix is consumed by a cross-attending action expert integrated over several solver steps. A single runtime serves seven architectures spanning five backbone and four action-head families behind one request/response protocol, with each model packaged as a self-contained bundle. On LIBERO-Object, the engine matches a state-of-the-art checkpoint to within one episode out of 200, and runs BitVLA at 100% success in 1.3 GiB of memory. The same bundle runs unchanged across three hardware tiers, from a consumer GPU down to an 8 GB embedded module. A cross-hardware roofline analysis shows that batch-1 VLA inference is compute-bound, so utilization rather than bandwidth is the deployment lever; an IMMA ladder GEMM derived from this analysis cuts BitVLA per-step latency by 4.5x. We then frame an on-robot stress test on an ALOHA arm that isolates the latency constraint under which a learned VLA must replan against a moving target on the hardware it was trained for. Code, demo videos, and the reproducible benchmark scaffold are available at https://fai-modelopt-tech.github.io/vla-cpp.github.io/.

Community

Sign up or log in to comment

Get this paper in your agent:

hf papers read 2606.08094
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2606.08094 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2606.08094 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2606.08094 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.