Add exception handling for numerical errors #13026
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/pytorch/executorch/13026
Note: Links to docs will display an error until the docs builds have been completed. ✅ No FailuresAs of commit cd911de with merge base bedce91 ( This comment was automatically generated by Dr. CI and updates every 15 minutes. |
meta-cla
bot
added
the
CLA Signed
|
This pull request was exported from Phabricator. Differential Revision: D79065198 |
This PR needs a
|
Summary: As titled. Instead of skipping, those tests will compare the errors to the existing values. Remove all updated tolerances from the runtime update side and make it an expected numerical accuracy. We should open tasks to trace the (large) errors, will do that as a follow up. On RT600, WW stage2, rnnt predictor and asr joiner are all showing flakiness. Opened T232829844 to track. Timeouts are still skipped for now. Reviewed By: abeakkas, zonglinpeng Differential Revision: D79065198
facebook-github-bot
force-pushed
the
export-D79065198
branch
from
8c51711 to
cd911de
Compare
|
This pull request was exported from Phabricator. Differential Revision: D79065198 |
Differential Revision: D79065198 Pull Request resolved: pytorch#13026
Summary:
As titled. Instead of skipping, those tests will compare the errors to the existing values.
Remove all updated tolerances from the runtime update side and make it an expected numerical accuracy. We should open tasks to trace the (large) errors, will do that as a follow up.
On RT600, WW stage2, rnnt predictor and asr joiner are all showing flakiness. Opened T232829844 to track.
Timeouts are still skipped for now.
Reviewed By: abeakkas
Differential Revision: D79065198