FocsleFo’c’sle
SI

OpenVLA-Edge

47%
by Stanford IRIS

Edge-distilled OpenVLA. The smallest practical VLA you can put on an AGX Orin without compromising the policy.

Vision-Language-ActionApache-2.0INT8MIXEDvlaopenxrobotics
41K downloads 1.2K deploymentsUpdated Apr 21, 2028
Headline:38.2ms · NVIDIA Jetson Thor · MIXED
arXiv
OverviewBenchmarks3Sim ResultsDeploy3FilesDiscussion23

Deploy OpenVLA-Edge

Pick a chip family. We hand you the artifacts (HEF, TRT engine, Core ML, ONNX) plus a one-click endpoint deploy. For private endpoints, on-prem deploy, or air-gapped distribution, see Enterprise.

NNVIDIA Jetson AGX Orin
# Build a TensorRT engine
$ focsle pull stanford-iris/openvla-edge --target jetson-agx-orin
$ focsle build trt --plan openvla-edge.plan \
    --precision mixed \
    --workspace 4G

# Run with TensorRT
import focsle.runtime as fr
m = fr.load("openvla-edge.plan", target="trt")
out = m.run(frame)

One-click endpoint

Spins up a managed endpoint in the closest region. Pro and above.

Or deploy yourself