From 967e0554436f49fa9b852bf95ebac4364a6eef0b Mon Sep 17 00:00:00 2001 From: Chen Lai Date: Mon, 21 Apr 2025 22:58:35 -0700 Subject: [PATCH] Update readme for qcom example (#10331) Summary: Pull Request resolved: https://github.com/pytorch/executorch/pull/10331 As title, add more comments for the docs Reviewed By: kirklandsign Differential Revision: D73382201 --- examples/qualcomm/README.md | 13 ++++++++++++- 1 file changed, 12 insertions(+), 1 deletion(-) diff --git a/examples/qualcomm/README.md b/examples/qualcomm/README.md index 04354cda3f6..d33d4d2c52b 100644 --- a/examples/qualcomm/README.md +++ b/examples/qualcomm/README.md @@ -44,13 +44,24 @@ commands in the `SimpleADB` class inside [utils.py](utils.py). ## Please use python xxx.py --help for information of each examples. -Some CLI examples here. Please adjust according to your environment: +Some CLI examples here. Please adjust according to your environment. If you want to export the model without running it, please add `-compile_only` to the command.: #### First switch to following folder ```bash cd $EXECUTORCH_ROOT/examples/qualcomm/scripts ``` +## Simple Examples to Verify the Backend is Working +```bash +python export_example.py -m add -g +``` + +It will generate a simple add model targeting for "SM8550". You can manually push the `add.pte` file to the device following https://pytorch.org/executorch/stable/build-run-qualcomm-ai-engine-direct-backend.html and run it with + +```bash +./qnn_executor_runner --model_path add.pte +``` + #### For MobileNet_v2 ```bash python mobilenet_v2.py -s -m "SM8550" -b path/to/build-android/ -d /path/to/imagenet-mini/val