Fixes issues with NLP pipelines when data is not truncated #316
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
Remove checks preventing slice operations when the length of the meta doesn't match the length of the tensors
…f they didn't we wouldn't have the seq_ids array to work with, replacing dead if branch with an assert
…nd offsets shouldn't match the inference offsets as this is a new array. Always use seq_ids to determine indexes of probs
dagardner-nv
added
non-breaking
…f the same length
dagardner-nv
added
3 - Ready for Review
and removed
DO NOT MERGE
dagardner-nv
changed the title
|
rerun tests |
|
rerun tests |
mdemoret-nv
approved these changes
Aug 8, 2022
|
rerun tests |
|
@gpucibot merge |
ghost
merged commit
This pull request was closed.
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Outdated suggestions cannot be applied.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.
TensorObject::read_elementas suggested in description in [BUG] SID Crash with--use_cpp=Trueand--truncation=False#305seq_idsarray is used to perform reduction of the rows. Such that if rows 5,6 & 7 of the output results map to row 5 in the dataframe, the max value of each row is stored in the response output.MatxUtil::reduce_maxto perform reduction.fixes #305