Fix QNN online-prepare graph handle retrieval

[sylvesterkaczmarek]

Fixes #21804.

QnnContext::Configure() registers DLC graphs into the QNN context for ONLINE_PREPARE before QnnGraph::Configure() runs. The graph configuration path then skipped both graph creation and graph retrieval, leaving graph_handle null and storing it in handle_.

This change retrieves already-registered DLC graphs with qnn_graph_retrieve, matching the deserialization path, applies AfterRetrieveGraph, and defensively rejects a null graph handle before bookkeeping.

Validation: adds a dedicated qnn_online_prepare backend test flow and wires it into QNN pull-request and scheduled CI so this runtime path is exercised alongside the existing QNN flow. The branch is rebased on current main and kept to one commit.

cc @cbilgin @psiddh

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/21860

• 📄 Preview Python docs built from this PR

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

❌ 1 Awaiting Approval, 1 New Failure

As of commit 6b1af15 with merge base bd2e855 ():

AWAITING APPROVAL - The following workflow needs approval before CI can run:

• periodic (gh)

NEW FAILURE - The following job has failed:

• pull / test-static-llama-qnn-linux (stories_260k_bc) / linux-job (gh)
  test_llama_stories_260k

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

[meta-cla]

Hi @sylvesterkaczmarek!

Thank you for your pull request and welcome to our community.

Action Required

In 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.

Process

In 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 CLA signed. The tagging process may take up to 1 hour after signing. Please give it that time before contacting us about it.

If you have received this in error or have any questions, please contact us at cla@meta.com. Thanks!

[linux-foundation-easycla]

The committers listed above are authorized under a signed CLA.

• ✅ login: sylvesterkaczmarek / name: Sylvester Kaczmarek (487b3ea)

[sylvesterkaczmarek]

@pytorchbot label "release notes: qualcomm"

[meta-cla]

Thank you for signing our Contributor License Agreement. We can now accept your code for this (and any) Meta Open Source project. Thanks!

[sylvesterkaczmarek]

CI is currently blocked on fork-workflow approval rather than a test failure. Dr. CI reports no failed jobs, both CLA checks are satisfied, and the QNN workflow has not started yet. Could a maintainer please approve the pending workflows, especially Test QNN Backend, Test QNN Windows MSVC build, and Lint, so the change can receive actual CI validation? Thanks.

[nil-is-all]

Hi @sylvesterkaczmarek, thanks for the PR and sorry for the delay. Running CI now

[chenweng-quic]

withdraw approval since I cannot reproduce issue mentioned in #21804 (comment)

[chenweng-quic]

withdraw approval