Fail the benchmark job if the export step fails #8786
Merged
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Outdated suggestions cannot be applied.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.
In this example, https://github.com./pytorch/executorch/actions/runs/13511586696/job/37752729714,
mv3
withmps
backend failed to export, but its corresponding benchmark job was green. The benchmark app didn't consider this as a failure when it didn't run any benchmark. IMO, if there was no model, it would be clearer to fail the job instead.(also fix the default model from
stories110M
tollama
as the former isn't a valid name anymore)cc @yangw-dev
Testing
https://github.com./pytorch/executorch/actions/runs/13577012355/job/37956751928#step:16:1126 where the corresponding benchmark jobs failed when there was no exported model