Qualcomm AI Engine Direct - docs fix

[DannyYuyang-quic]

Summary

update README on python dependencies and recommended QNN version

cc @cccclai @winskuo-quic @shewu-quic @haowhsu-quic @cbilgin

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14881

• 📄 Preview Python docs built from this PR

Note: Links to docs will display an error until the docs builds have been completed.

❌ 2 New Failures, 11 Pending

As of commit 41f2c2e with merge base bba9d26 ():

NEW FAILURES - The following jobs have failed:

• pull / test-samsung-models-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 94e0a35228ead8292d5261d0fee74f0cf5ec2e8fa01dcc75f1702156a28f79b5 /exec failed with exit code 1
• Test CUDA Builds / test-voxtral-cuda-e2e / linux-job (gh)
  RuntimeError: Command docker exec -t 463c2cc079c1c20f63bb6f71014993ee81a6a51d33ac85454250323a3bdb9e2d /exec failed with exit code 2

This comment was automatically generated by Dr. CI and updates every 15 minutes.

[DannyYuyang-quic]

@pytorchbot label "release notes: qualcomm"

[kimishpatel]

@cccclai we need to update these instructions. We shouldnt need to download sdk with qnn pip wheel. Make this either optional or remove it entirely. I would prefer latter because it avoid confusion

[cccclai]

pip wheel release hasn't finished yet. The nightly build is based on viable/strict and it has been stuck for a week, which doesn't include our latest commit for the fix. After it's verified, I can add a session and move this part to build from source session

[abhinaykukkadapu]

I had to install lm_eval too.

[cccclai]

lm_eval is only for llama I think

[abhinaykukkadapu]

Thanks, I see it is part of examples/models/llama/install_requirements.sh, may be we should mention this in the instructions to run llama models?

[cccclai]

Yeah I think it's reasonable to have it as part of the instructions to run llama models

[DannyYuyang-quic]

I’ve just added the instruction at this line

[cccclai]

I think these part

cmake .. \
  -DCMAKE_INSTALL_PREFIX=$PWD \
  -DEXECUTORCH_BUILD_QNN=ON \
  -DQNN_SDK_ROOT=${QNN_SDK_ROOT} \
  -DEXECUTORCH_BUILD_DEVTOOLS=ON \
  -DEXECUTORCH_BUILD_EXTENSION_MODULE=ON \
  -DEXECUTORCH_BUILD_EXTENSION_TENSOR=ON \
  -DEXECUTORCH_ENABLE_EVENT_TRACER=ON \
  -DPYTHON_EXECUTABLE=python3
...
cp -f backends/qualcomm/PyQnnManagerAdaptor.cpython-310-x86_64-linux-gnu.so $EXECUTORCH_ROOT/backends/qualcomm/python
cp -f backends/qualcomm/PyQnnWrapperAdaptor.cpython-310-x86_64-linux-gnu.so $EXECUTORCH_ROOT/backends/qualcomm/python
# Workaround for .fbs files in exir/_serialize
cp $EXECUTORCH_ROOT/schema/program.fbs $EXECUTORCH_ROOT/exir/_serialize/program.fbs
cp $EXECUTORCH_ROOT/schema/scalar_type.fbs $EXECUTORCH_ROOT/exir/_serialize/scalar_type.fbs

are covered by the build.sh already and good to remove.

[DannyYuyang-quic]

cd $EXECUTORCH_ROOT
mkdir build-android
cd build-android
# build executorch & qnn_executorch_backend
cmake .. \
    -DCMAKE_INSTALL_PREFIX=$PWD \
    -DEXECUTORCH_BUILD_QNN=ON \
    -DQNN_SDK_ROOT=$QNN_SDK_ROOT \
    -DEXECUTORCH_BUILD_DEVTOOLS=ON \
    -DEXECUTORCH_BUILD_EXTENSION_MODULE=ON \
    -DEXECUTORCH_BUILD_EXTENSION_TENSOR=ON \
    -DEXECUTORCH_ENABLE_EVENT_TRACER=ON \
    -DPYTHON_EXECUTABLE=python3 \
    -DCMAKE_TOOLCHAIN_FILE=$ANDROID_NDK_ROOT/build/cmake/android.toolchain.cmake \
    -DANDROID_ABI='arm64-v8a' \
    -DANDROID_PLATFORM=android-30

# nproc is used to detect the number of available CPU.
# If it is not applicable, please feel free to use the number you want.
cmake --build $PWD --target install -j$(nproc)

cmake ../examples/qualcomm \
    -DCMAKE_TOOLCHAIN_FILE=$ANDROID_NDK_ROOT/build/cmake/android.toolchain.cmake \
    -DANDROID_ABI='arm64-v8a' \
    -DANDROID_PLATFORM=android-30 \
    -DCMAKE_PREFIX_PATH="$PWD/lib/cmake/ExecuTorch;$PWD/third-party/gflags;" \
    -DCMAKE_FIND_ROOT_PATH_MODE_PACKAGE=BOTH \
    -DPYTHON_EXECUTABLE=python3 \
    -Bexamples/qualcomm

cmake --build examples/qualcomm -j$(nproc)

# qnn_executor_runner can be found under examples/qualcomm
# The full path is $EXECUTORCH_ROOT/build-android/examples/qualcomm/executor_runner/qnn_executor_runner
ls examples/qualcomm

@cccclai, thanks for the feedback! I think it's reasonable to rely on the build.sh instructions. I'll also remove the steps above, since they're already covered by the script too.

[cccclai]

Thanks for the doc improvement!

[cccclai]

@pytorchbot cherry-pick --onto release/1.0 -c docs

[pytorchbot]

Cherry picking #14881

The cherry pick PR is at #14948 The following tracker issues are updated:

• [v1.0.0] Release Tracker #14288 (comment)

Details for Dev Infra team

Raised by workflow job