[Qualcomm] Fix InsertIOQDQ KeyError for dequantize encodings

[abhinaykukkadapu]

Summary:
q_dq_map only contains quantize ops as keys, so when a node with a dequantize encoding (e.g. a pre-quantized LLM parameter) feeds the output node, the lookup crashes with a KeyError.

Use q_dq_map.get(encoding, encoding) so that dequantize encodings fall back to themselves — which is already the correct dequantize target for output boundary insertion.

Fixes #17732

[pytorch-bot]

🔗 Helpful Links

🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/18601

• 📄 Preview Python docs built from this PR

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

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

[haowhsu-quic]

Hi @abhinaykukkadapu, the root cause of #17732 was having too many shards due to unsupported op like #16690. I believe the solution of #17732 has already been addressed in #17194.

[abhinaykukkadapu]

Hi @abhinaykukkadapu, the root cause of #17732 was having too many shards due to unsupported op like #16690. I believe the solution of #17732 has already been addressed in #17194.

Thanks for taking a look, right this task is not 1-1 mapping but there is a comment on the task that refers to unavail dq in the map: #17732 (comment)

Also #17194 got reverted in #17385 this change with list() semantics should pass the tests.

[abhinaykukkadapu]

Hi @abhinaykukkadapu, the root cause of #17732 was having too many shards due to unsupported op like #16690. I believe the solution of #17732 has already been addressed in #17194.

Thanks for taking a look, right this task is not 1-1 mapping but there is a comment on the task that refers to unavail dq in the map: #17732 (comment)

Also #17194 got reverted in #17385 this change with list() semantics should pass the tests.

Something happened when force pushing the PR after rebase, it got merged to a feature branch with no files, opening a new PR: #18622