Qualcomm AI Engine Direct - Suite Operator Test Support Part 2#14869
Merged
GregoryComer merged 2 commits intorelease/1.0from Oct 11, 2025
Merged
Qualcomm AI Engine Direct - Suite Operator Test Support Part 2#14869GregoryComer merged 2 commits intorelease/1.0from
GregoryComer merged 2 commits intorelease/1.0from
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/14869
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 Cancelled Job, 3 PendingAs of commit 2ead920 with merge base e0dda90 ( CANCELLED JOB - The following job was cancelled. Please retry:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
### Summary Support following OPs - Threshold OP - negative dims permute - sqrt unit test modified to use desired input rather than random values - rsqrt unit test modified to use desired input rather than random values - per channel conv3d support For the sqrt/rsqrt, I believe the sample input for each UT is using `rand` instead of `randn` on purpose to prevent negative numbers input, however, if we don't set `generate_random_test_inputs=False`, then later on it will be using random values consisting of negative numbers, causing `nan` showing up on output. If everything works as expected, we should pass 6 more tests, bringing pass rate from **90.7% -> 91.5%** ### Test plan UT added cc @cccclai @shewu-quic @haowhsu-quic @DannyYuyang-quic @cbilgin (cherry picked from commit 0e74a17)
GregoryComer
force-pushed
the
cherry-pick-14848-by-pytorch_bot_bot_
branch
from
96fae0b to
59617fb
Compare
Member
|
Rebasing to test against the latest. |
Member
|
@cccclai Can you take a look at the failures on this PR? Looks like it's failing to import: ImportError: cannot import name 'merge_decomposed_graph' from 'executorch.backends.qualcomm._passes.utils' |
Contributor
oh can it be due to this pr not cherry pick? #14378 |
Contributor
|
@GregoryComer can you merge #14947 first? |
Member
|
#14947 is merged. I fixed a minor merge conflict (low risk) and will merge if CI is clean. |
GregoryComer
approved these changes
Oct 11, 2025
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
4 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
Support following OPs
For the sqrt/rsqrt, I believe the sample input for each UT is using
randinstead ofrandnon purpose to prevent negative numbers input, however, if we don't setgenerate_random_test_inputs=False, then later on it will be using random values consisting of negative numbers, causingnanshowing up on output.If everything works as expected, we should pass 6 more tests, bringing pass rate from 90.7% -> 91.5%
Test plan
UT added
cc @cccclai @shewu-quic @haowhsu-quic @DannyYuyang-quic @cbilgin