FocsleFo’c’sle
AE

DocLayout-Edge

8%
by Adept-Edge

Layout-aware document parser. Pairs with PaddleOCR-v5 for end-to-end PDF understanding on-device.

OCRApache-2.0INT8FP16doc-ailayout
36K downloads 1.2K deploymentsUpdated Mar 8, 2028
Headline:22.6ms · Snapdragon 8 Gen 3 NPU · INT8
OverviewBenchmarks4Sim ResultsDeploy4FilesDiscussion23

Deploy DocLayout-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 Orin Nano
# Build a TensorRT engine
$ focsle pull adept-edge/doclayout-edge --target jetson-orin-nano
$ focsle build trt --plan doclayout-edge.plan \
    --precision fp16 \
    --workspace 4G

# Run with TensorRT
import focsle.runtime as fr
m = fr.load("doclayout-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