Qualcomm AI Engine Direct - Custom op example fixes

[qti-mmadhava]

Qualcomm AI Engine Direct - Custom op example fixes

Summary

• Fixed bug in custom_op example, where use_fp16 was failing, due to quantizer being called.
• Set LD_LIBRARY_PATH and ADSP_LIBRARY_PATH prior to executing on-device.
• Added debug flag to custom_op example, so that DSP logs are captured by adb logcat

Test plan

python3 examples/qualcomm/custom_op/custom_ops_1.py --build_folder build-android -s $ANDROID_SERIAL -H $ADB_HOST -m SM8650 --op_package_dir examples/qualcomm/custom_op/example_op_package_htp/ExampleOpPackage --build_op_package --debug --use_fp16

cc @cccclai @cbilgin

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18024

• 📄 Preview Python docs built from this PR

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

❌ 56 New Failures, 2 Unrelated Failures

As of commit eeff431 with merge base 47b8d1d ():

NEW FAILURES - The following jobs have failed:

• Build Presets / apple (ios-simulator) / build (gh)
• Build Presets / apple (ios) / build (gh)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 1
• Build Presets / apple (llm) / build (gh)
  RuntimeError: Command bash /Users/runner/work/_temp/exec_script failed with exit code 1
• Build Presets / apple (macos) / build (gh)
• Build Presets / apple (profiling) / build (gh)
• Build Presets / apple (pybind) / build (gh)
• Build Presets / linux (linux, linux.2xlarge, executorch-ubuntu-22.04-clang12) / build (gh)
  RuntimeError: Command docker exec -t 9dd0ad13f1041fb3f16f2b8e5a4f8ed7d70c16cf31a2d1a59c89091cf69616c8 /exec failed with exit code 1
• Build Presets / linux (linux, linux.arm64.2xlarge, executorch-ubuntu-22.04-gcc11-aarch64) / build (gh)
  RuntimeError: Command docker exec -t 0d81a20c7bf16656daf036016cf86463f52157d78373e8082a9557e4d2381384 /exec failed with exit code 1
• Build Presets / linux (llm, linux.2xlarge, executorch-ubuntu-22.04-clang12) / build (gh)
  RuntimeError: Command docker exec -t 73d532ad3aea71d51e5460a708b7a4a5d5fd6d1784bd83c7feee90daf24e4bd1 /exec failed with exit code 1
• Build Presets / linux (llm, linux.arm64.2xlarge, executorch-ubuntu-22.04-gcc11-aarch64) / build (gh)
  RuntimeError: Command docker exec -t 3b00a80e7e755025fcc4a705f5660af935bd05f06f5272f86ef27ea40fe0da77 /exec failed with exit code 1
• Build Presets / linux (pybind, linux.2xlarge, executorch-ubuntu-22.04-clang12) / build (gh)
• Build Presets / linux (pybind, linux.arm64.2xlarge, executorch-ubuntu-22.04-gcc11-aarch64) / build (gh)
  RuntimeError: Command docker exec -t 76fc6f1da98ba84892d969b43c94dd7bdac18fd9a351018fab608914755b7c3c /exec failed with exit code 1
• Build Presets / windows (pybind) / build (gh)
  Process completed with exit code 1.
• Build Presets / windows (windows) / build (gh)
• Build Presets / zephyr (zephyr) / build (gh)
  RuntimeError: Command docker exec -t 38bd11b9d318f5215fb7d7fabb7134927f8528058546295f6fe86aee1755209c /exec failed with exit code 1
• Lint / link-check / lint-file-size (gh)
  Process completed with exit code 1.
• Lint / lintrunner-mypy (gh)
  >>> Lint for test/end2end/test_end2end.py:
• pull / test-binary-size-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 942d6abcb9d7d088474aae861b0fd05ae5761de4dc1cd23c97fea9305351e6a9 /exec failed with exit code 1
• pull / test-binary-size-linux-gcc / linux-job (gh)
  RuntimeError: Command docker exec -t b0d828e657a1f9ad5f41fc170d999f023b10f4002db28985e2be2aa88b717b38 /exec failed with exit code 1
• pull / test-coreml-bc-macos (macos-m1-stable) / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
• pull / test-coreml-bc-macos (macos-m2-stable) / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
• pull / test-lora-multimethod-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 53215ae4fec304db529918b3e4d444772bda0ef80140b202b42da7c4e0b55b5e /exec failed with exit code 127
• pull / test-parakeet-xnnpack-linux / linux-job (gh)
  RuntimeError: Command docker exec -t a9512311adf67e74839c555a846974f7bf24b14a812212d6469e12835e145148 /exec failed with exit code 1
• pull / test-qnn-wheel-packages-linux (3.10) / linux-job (gh)
  RuntimeError: Command docker exec -t 598fe6bb4320731ed5106ca5e596893c008a0a7b1c24caf70b8c2866c7788d7a /exec failed with exit code 1
• pull / test-qnn-wheel-packages-linux (3.11) / linux-job (gh)
  RuntimeError: Command docker exec -t 1044cb92c881dfb3023e1808ac35bf84b377efeefa7a1f39970bf5d8c14c9845 /exec failed with exit code 1
• pull / test-qnn-wheel-packages-linux (3.12) / linux-job (gh)
  RuntimeError: Command docker exec -t 746358891c1dcd71466f6840944c6ea0a45867637ddd60b7e1f663879bb2dbc4 /exec failed with exit code 1
• pull / test-qnn-wheel-packages-linux (3.13) / linux-job (gh)
  RuntimeError: Command docker exec -t 4a85eb57a34fe163c91fa0cb367563cc67bb6a7529819ca7f02938cc56d02266 /exec failed with exit code 1
• pull / test-samsung-models-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 5bb852c254ec227a67a1d827507700f9e1d88f7e5c9c6869898746d9e89531ec /exec failed with exit code 127
• pull / test-samsung-quantmodels-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 93b5da5649fdf407cbf308e30e893925249a3f387cc97f51958ffb425d529c38 /exec failed with exit code 127
• pull / test-voxtral-realtime-xnnpack-linux / linux-job (gh)
  RuntimeError: Command docker exec -t be6402a41b2afa4f20d0cde4874e7b285ef0b62d33bb4619f17f7d54bac7371c /exec failed with exit code 1
• pull / test-vulkan-operators-linux / linux-job (gh)
  RuntimeError: Command docker exec -t 03820b22d9ee29bcff1c185f023bac7c1a5dd399c953eb23f69ffa1f7205a286 /exec failed with exit code 127
• pull / unittest / windows / windows-job (gh)
  Process completed with exit code 1.
• pull / unittest-arm-backend-with-no-deps (test_pytest_models_tosa) / linux-job (gh)
  /tmp/pip-build-env-9c836qee/overlay/lib/python3.10/site-packages/pybind11/include/pybind11/pybind11.h:2462:25: error: static assertion failed: def_property family does not currently support keep_alive. Use a py::cpp_function instead.
• pull / unittest-arm-backend-with-no-deps (test_pytest_ops_no_target) / linux-job (gh)
  /tmp/pip-build-env-jw4wsatq/overlay/lib/python3.10/site-packages/pybind11/include/pybind11/pybind11.h:2462:25: error: static assertion failed: def_property family does not currently support keep_alive. Use a py::cpp_function instead.
• pull / unittest-arm-backend-with-no-deps (test_pytest_ops_tosa) / linux-job (gh)
  /tmp/pip-build-env-as22w18p/overlay/lib/python3.10/site-packages/pybind11/include/pybind11/pybind11.h:2462:25: error: static assertion failed: def_property family does not currently support keep_alive. Use a py::cpp_function instead.
• pull / unittest-arm-backend-with-no-deps (test_run_tosa) / linux-job (gh)
  /tmp/pip-build-env-u6ufk6k2/overlay/lib/python3.10/site-packages/pybind11/include/pybind11/pybind11.h:2462:25: error: static assertion failed: def_property family does not currently support keep_alive. Use a py::cpp_function instead.
• pull / unittest-buck / linux / linux-job (gh)
  RuntimeError: Command docker exec -t 817665140b3e8603d3c18e94ab74e4a7ae33084aefb663e6b8d46aa4ef76b9fa /exec failed with exit code 3
• pull / unittest-editable / macos / macos-job (gh)
  export/tests/test_target_recipes.py::TestTargetRecipes::test_mv3_model
• pull / unittest-editable / windows / windows-job (gh)
  Process completed with exit code 1.
• pull / unittest-nxp-neutron / linux-job (gh)
  RuntimeError: Command docker exec -t da94053b352de38ae48936e01d00a88f01a3f8541eb5a6ea189efa1cd54a5c9d /exec failed with exit code 1
• Test CUDA Builds / check-all-cuda-builds (gh)
  Process completed with exit code 1.
• Test CUDA Builds / test-executorch-cuda-build-12.6 / linux-job (gh)
  RuntimeError: Command docker exec -t 8138cc73b9e797bb018ffcd779140e3da7a755d25d29ea5ad55aa24490cdf103 /exec failed with exit code 1
• Test CUDA Builds / test-executorch-cuda-build-12.8 / linux-job (gh)
  RuntimeError: Command docker exec -t 2ba4b491b4d8db49c0fbf72db2d4603a7321b3403cc247e6016233775293654c /exec failed with exit code 1
• Test CUDA Builds / test-executorch-cuda-build-12.9 / linux-job (gh)
  RuntimeError: Command docker exec -t 9a16de88b248e19b373d45faebc073890524bf2828d9a425438bf7e9f37065f5 /exec failed with exit code 1
• Test CUDA Builds / test-executorch-cuda-build-13.0 / linux-job (gh)
  RuntimeError: Command docker exec -t ced2793cbdfd2578c04ed17c591abe9d36b5f18de868a9e20199fe4e6de56eef /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (add_mul) / linux-job (gh)
  RuntimeError: Command docker exec -t 7fc6dc65827f98e48676b834493643fdd0b9e14b2c05327c3fbd23399808bda9 /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (add) / linux-job (gh)
  RuntimeError: Command docker exec -t b1f5dda290c401faeff98b54387fbbb0f0754897d0506fbaedeb9c4c0c417e12 /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (conv1d) / linux-job (gh)
  RuntimeError: Command docker exec -t 4c3e88df8158736e0f4bb049c949728588e30cf0cb4702e1d3a8992034666d15 /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (linear) / linux-job (gh)
  RuntimeError: Command docker exec -t be6f350207e1c1c493df26be5c528d8c1d5a7d405063884a583c5c1fae29dd98 /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (mv2) / linux-job (gh)
  RuntimeError: Command docker exec -t 4d26f0ffc079b383bb02d2b93a7e2747d67bc0f931d5925b67e34434e1e2e40f /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (mv3) / linux-job (gh)
  RuntimeError: Command docker exec -t 85efaab39f324af677ba51351b65edd14b3d1a8da2b2aa0299ff465417cd1ff5 /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (resnet18) / linux-job (gh)
  RuntimeError: Command docker exec -t a68ca357ea158507365ec4f9dd510baba4d07bb953b122cf0aedc0fbc715a0bb /exec failed with exit code 1
• Test CUDA Builds / test-models-cuda (sdpa) / linux-job (gh)
  RuntimeError: Command docker exec -t a0b229b7cdf8fc735f7a203b2b2dfab3903f7c8d17c937b4126655d97af4fb4f /exec failed with exit code 1
• Test CUDA Builds / unittest-cuda / linux-job (gh)
  RuntimeError: Command docker exec -t 47296f887519cf9e0a18f6a61da1b9a7c3604c20427fd0130d39b7a26df678ee /exec failed with exit code 1
• Test Metal Backend / test-executorch-metal-build / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1
• Test Metal Backend / test-metal-backend-modules / macos-job (gh)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 1

FLAKY - The following job failed but was likely due to flakiness present on trunk:

• pull / test-moshi-linux / linux-job (gh) (matched linux rule in flaky-rules.json)
  E: Failed to fetch http://security.ubuntu.com/ubuntu/pool/main/g/gcc-12/libgfortran5_12.3.0-1ubuntu1%7e22.04.2_amd64.deb 404 Not Found [IP: 185.125.190.82 80]

BROKEN TRUNK - The following job failed but was present on the merge base:

👉 Rebase onto the `viable/strict` branch to avoid these failures

• pull / unittest-buck / macos / macos-job (gh) (trunk failure)
  RuntimeError: Command bash /Users/ec2-user/runner/_work/_temp/exec_script failed with exit code 3

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

[github-actions]

This PR needs a release notes: label

If your change should be included in the release notes (i.e. would users of this library care about this change?), please use a label starting with release notes:. This helps us keep track and include your important work in the next release notes.

To add a label, you can comment to pytorchbot, for example
@pytorchbot label "release notes: none"

For more information, see
https://github.com/pytorch/pytorch/wiki/PyTorch-AutoLabel-Bot#why-categorize-for-release-notes-and-how-does-it-work.

[qti-mmadhava]

Hi @cccclai, @abhinaykukkadapu,
This PR includes some minor fixes and updates to the qualcomm custom_op example.
When you have time, could you please help review?
Thanks

[digantdesai]

PR looks ok. Are the CI failures unrelated?

[abhinaykukkadapu]

@digantdesai I think it is based on a very old base

It’s [521 commits](https://github.com/pytorch/executorch/compare/6abcb53b...main) behind (base commit: https://github.com/pytorch/executorch/commit/6abcb53bf029e2e66793b234bd96384d54620bf6)
Hang in there while we check the branch's status.

@qti-mmadhava can you pull and rebase to main.