Fix local QNN AAR setup in the Android LlamaDemo guide - #266
eoinjordan wants to merge 1 commit into
Conversation
|
Hi @eoinjordan! Thank you for your pull request and welcome to our community. Action RequiredIn order to merge any pull request (code, docs, etc.), we require contributors to sign our Contributor License Agreement, and we don't seem to have one on file for you. ProcessIn order for us to review and merge your suggested changes, please sign at https://code.facebook.com/cla. If you are contributing on behalf of someone else (eg your employer), the individual CLA may not be sufficient and your employer may need to sign the corporate CLA. Once the CLA is signed, our tooling will perform checks and validations. Afterwards, the pull request will be tagged with If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks! |
Signed |
|
Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks! |
|
Hi @kirklandsign if you get a chance can you review? I have tested it on my handset with QNN and its working. Do you need screenshots etc? |
Following the QNN LlamaDemo guide instructions I confirmed the copied AAR needs useLocalAar=true to be selected. Otherwise the app can report Invalid model type category: 4 (QNN) as raised in #227
This PR:
Adds the local AAR setup for Android Studio and command-line builds, invokes the build script with Bash, and gives a clear error if the AAR is missing. Keeps category 4 for the QNN runner.
Validation (on 8s Gen 3 (Ultra RAZR 50))
To validate from an onnx model :
You need to make sure a compatible, or compiled from onnx follow steps here - https://workbench.aihub.qualcomm.com/docs/hub/compile_examples.html#compile-onnx