[DevX] Skip disabled configs for benchmarking #7868
Merged
Conversation
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
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/7868
Note: Links to docs will display an error until the docs builds have been completed. ⏳ 16 Pending, 2 Unrelated FailuresAs of commit 1a4cf63 with merge base d68ca28 ( BROKEN TRUNK - The following jobs failed but were 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. |
facebook-github-bot
added
the
CLA Signed
guangy10
temporarily deployed
to
upload-benchmark-results
GitHub Actions
Inactive
guangy10
temporarily deployed
to
upload-benchmark-results
GitHub Actions
Inactive
guangy10
force-pushed
the
benchmark_skip_disabled_configs
branch
from
c4a2c5d to
e0efaba
Compare
|
Subscribed @kimishpatel @digantdesai to DevX related work. |
|
@guangy10 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
guangy10
force-pushed
the
benchmark_skip_disabled_configs
branch
from
e0efaba to
1a4cf63
Compare
|
@guangy10 has imported this pull request. If you are a Meta employee, you can view this diff on Phabricator. |
YIWENX14
pushed a commit
that referenced
this pull request
Jan 28, 2025
Skip disabled configs for benchmarking Co-authored-by: Github Executorch <github_executorch@arm.com>
zonglinpeng
pushed a commit
to zonglinpeng/executorch
that referenced
this pull request
Jan 30, 2025
Skip disabled configs for benchmarking Co-authored-by: Github Executorch <github_executorch@arm.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Some benchmark jobs have been failing for a long time, creating misleading signal about what expected and unexpected by looking at those jobs. For example:
The reason is that those configs are either not supported or having bugs to be fixed. There is no way to specify which config for which model should be disabled/bypassed in the past.
This PR adds the ability to do so. Going forward, the nightly benchmark jobs (
android-perfandapple-perf) should always be green, if not, it clearly signals that some configs are failing/flaky and should be fixed.This PR also set a process to track disabled model+config in the GitHub Issue, the test will catch it if trying to disable a config for a model but not providing a link to GitHub Issue. The enforcement is to make sure regressions is tracked properly.
Test:
qnn_q8config is skipped forw2l: https://github.com/pytorch/executorch/actions/runs/12920378484mpsconfig is skipped formobilebert: https://github.com/pytorch/executorch/actions/runs/12920397985