Build qwen3 with qnn backend fails

I'm trying to test Qwen3-0.6B model on Android with QNN backend, but struggling to export the model into a .pte file.

While exporting the model with the following command, I got an error [ERROR] [Qnn ExecuTorch]: Cannot Open QNN library libQnnHtp.so, with error: libc++.so.1: cannot open shared object file: No such file or directory. However, LD_LIBRARY_PATH is set properly and there's libQnnHtp.so file in the path.

python -m examples.models.llama.export_llama \
  --model qwen3-0_6b \
  --params examples/models/qwen3/0_6b_config.json \
  --use_kv_cache \
  --qnn \
  --pt2e_quantize qnn_16a4w \
  --metadata '{"get_bos_id": 151644, "get_eos_ids":[151645]}' \
  --output_name="qwen3-0_6b_qnn.pte" \
  --disable_dynamic_shape \
  --calibration_tasks wikitext --calibration_limit 1 --calibration_seq_length 128 --calibration_data "<|start_header_id|>system<|end_header_id|>\n\nYou are a funny chatbot.<|eot_id|><|start_header_id|>user<|end_header_id|>\n\nCould you tell me about Facebook?<|eot_id|><|start_header_id|>assistant<|end_header_id|>\n\n" \
  --verbose

I used following commands to setup executorch with qnn backend and llama runner with qnn backend.

• setup

cd $EXECUTORCH_ROOT
mkdir build-x86
cd build-x86
# Note that the below command might change.
# Please refer to the above build.sh for latest workable commands.
cmake .. \
  -DCMAKE_INSTALL_PREFIX=$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

# 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 $PWD --target "PyQnnManagerAdaptor" "PyQnnWrapperAdaptor" -j$(nproc)

# install Python APIs to correct import path
# The filename might vary depending on your Python and host version.
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

• runner

cmake -DCMAKE_TOOLCHAIN_FILE=$ANDROID_NDK/build/cmake/android.toolchain.cmake \
    -DANDROID_ABI=arm64-v8a \
    -DANDROID_PLATFORM=android-23 \
    -DCMAKE_INSTALL_PREFIX=cmake-out-android \
    -DCMAKE_BUILD_TYPE=Release \
    -DEXECUTORCH_BUILD_EXTENSION_DATA_LOADER=ON \
    -DEXECUTORCH_BUILD_EXTENSION_MODULE=ON \
    -DEXECUTORCH_BUILD_EXTENSION_TENSOR=ON \
    -DEXECUTORCH_ENABLE_LOGGING=1 \
    -DPYTHON_EXECUTABLE=python \
    -DSUPPORT_REGEX_LOOKAHEAD=ON \
    -DEXECUTORCH_BUILD_QNN=ON \
    -DQNN_SDK_ROOT=$QNN_SDK_ROOT \
    -DEXECUTORCH_BUILD_KERNELS_OPTIMIZED=ON \
    -DEXECUTORCH_BUILD_KERNELS_QUANTIZED=ON \
    -DEXECUTORCH_BUILD_KERNELS_CUSTOM=ON \
    -Bcmake-out-android .

cmake --build cmake-out-android -j16 --target install --config Release

cmake  -DCMAKE_TOOLCHAIN_FILE=$ANDROID_NDK/build/cmake/android.toolchain.cmake \
    -DANDROID_ABI=arm64-v8a \
    -DANDROID_PLATFORM=android-23 \
    -DCMAKE_INSTALL_PREFIX=cmake-out-android \
    -DCMAKE_BUILD_TYPE=Release \
    -DPYTHON_EXECUTABLE=python \
    -DSUPPORT_REGEX_LOOKAHEAD=ON \
    -DEXECUTORCH_BUILD_QNN=ON \
    -DQNN_SDK_ROOT=$QNN_SDK_ROOT \
    -DEXECUTORCH_BUILD_KERNELS_OPTIMIZED=ON \
    -DEXECUTORCH_BUILD_KERNELS_QUANTIZED=ON \
    -DEXECUTORCH_BUILD_KERNELS_CUSTOM=ON \
    -Bcmake-out-android/examples/models/llama \
    examples/models/llama

cmake --build cmake-out-android/examples/models/llama -j16 --config Release

Environments

• executorch: main branch(b173722085b3f555d6ba4533d6bbaddfd7c71144)
• development platform: Ubuntu 20.04
• QNN version: 2.32.0.250228
• Android NDK: r28b

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

Reproduce the failure from examples/models/llama/export_llama using the QNN 2.32.0.250228 SDK and Android NDK r28b setup described in the issue. Trace the QNN library-loading path and verify the host export environment; done means the Qwen3 command produces qwen3-0_6b_qnn.pte without the missing libc++.so.1 error.