Add GenAi-PA error handling #483
Merged
Conversation
This file contains 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
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
rmccorm4
reviewed
Mar 1, 2024
rmccorm4
reviewed
Mar 1, 2024
rmccorm4
reviewed
Mar 1, 2024
|
@dyastremsky @nv-braf I think the logic for the separate directory was that there might be more input specific files coming. The separate directory was prefetching organization that was going to be necessary in the short-mid term. |
debermudez
reviewed
Mar 1, 2024
There was a problem hiding this comment.
Agree with @rmccorm4 suggestions. Update those sections and this is good to go in.
Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
rmccorm4
approved these changes
Mar 1, 2024
Thanks for the corrections, @rmccorm4! All fixed. Understood on the structure, @nv-braf @debermudez. Thanks for the clarification, that sounds good! |
debermudez
approved these changes
Mar 1, 2024
debermudez
pushed a commit
that referenced
this pull request
Mar 2, 2024
* Print exception when non-zero error code * Add test for GenAiPAException for nonzero exit * Revert format/comment changes. * Fix typo Co-authored-by: Ryan McCormick <rmccormick@nvidia.com> * Remove unnecessary return value Co-authored-by: Ryan McCormick <rmccormick@nvidia.com> --------- Co-authored-by: Ryan McCormick <rmccormick@nvidia.com> WIP clean up and link up llm_inputs
debermudez
pushed a commit
that referenced
this pull request
Mar 12, 2024
* Print exception when non-zero error code * Add test for GenAiPAException for nonzero exit * Revert format/comment changes. * Fix typo Co-authored-by: Ryan McCormick <rmccormick@nvidia.com> * Remove unnecessary return value Co-authored-by: Ryan McCormick <rmccormick@nvidia.com> --------- Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
debermudez
pushed a commit
that referenced
this pull request
Mar 13, 2024
* Print exception when non-zero error code * Add test for GenAiPAException for nonzero exit * Revert format/comment changes. * Fix typo Co-authored-by: Ryan McCormick <rmccormick@nvidia.com> * Remove unnecessary return value Co-authored-by: Ryan McCormick <rmccormick@nvidia.com> --------- Co-authored-by: Ryan McCormick <rmccormick@nvidia.com>
mc-nv
pushed a commit
that referenced
this pull request
Mar 13, 2024
* Print exception when non-zero error code * Add test for GenAiPAException for nonzero exit * Revert format/comment changes. * Fix typo Co-authored-by: Ryan McCormick <rmccormick@nvidia.com> * Remove unnecessary return value Co-authored-by: Ryan McCormick <rmccormick@nvidia.com> --------- Co-authored-by: Ryan McCormick <rmccormick@nvidia.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.
This PR adds exception handling to the core logic of GenAi-PA and prints an error when perf_analyzer returns a non-zero code. There is also an added exception make sure that run() returns this exception.
This also moves llm_inputs.py underneath the genai_pa to help start integrating the components of GenAi-PA. This organization seems logical to me and consistent with the way the Model Analyzer code is currently written, but I am open to feedback here. (CC: @nv-braf, let me know if you think this should be reverted.)
Passing tests:
Additional error log when there is a failure (in this case, a non-zero exit code from Perf Analyzer):
