[DO NOT MERGE] Qualcomm AI Engine Direct - Reproduce Cat Error#19182
Draft
winskuo-quic wants to merge 2 commits intopytorch:mainfrom
Draft
[DO NOT MERGE] Qualcomm AI Engine Direct - Reproduce Cat Error#19182winskuo-quic wants to merge 2 commits intopytorch:mainfrom
winskuo-quic wants to merge 2 commits intopytorch:mainfrom
Conversation
…h#19159) Summary: Replace the Qualcomm concat observer path with an explicit same-domain-or-requantize model for `aten.cat`. Preserve shared qparams for `pixel_shuffle` and `pixel_unshuffle`, extend `split_with_sizes_copy` coverage, and add regressions for mismatched `cat` branches plus value-preserving ops that must use `SharedQuantizationSpec`. Differential Revision: D102626539
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/19182
Note: Links to docs will display an error until the docs builds have been completed. ❗ 1 Active SEVsThere are 1 currently active SEVs. If your PR is affected, please view them below: ❌ 1 Awaiting Approval, 12 New Failures, 4 Unrelated FailuresAs of commit 9ad825b with merge base 2084866 ( NEW FAILURES - The following jobs have failed:
FLAKY - The following job failed but was likely due to flakiness present on trunk:
BROKEN TRUNK - The following jobs failed but was present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
Bot
added
the
CLA Signed
This PR needs a
|
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Please reproduce with the following command:
python backends/qualcomm/tests/test_qnn_delegate.py -k TestQNNQuantizedOperator.test_qnn_backend_cat_fixed_input --model SM8750 --device $DEVICE --build_folder build-androidWhen concat 2 input tensors:
torch.tensor([[[[-10.0, 2.0], [3.0, 4.0]]]]) torch.tensor([[[[1.0, 3.0], [8.0, 10.0]]]]),we should ensure smallest value and largest value of input is representable with quant spec, which is why we cannot reuse input[0] quant_spec and apply to rest of all.
If we lower this model with mainline, we can get reasonable quant_spec for graph and also reasonable output.
Mainline:
However, if we do it with this PR, we are getting quant_spec that cannot represent values from -10 to 10.
This PR (10 got clipped to 4 for last value):