Fix log_parsing example pipeline null output issue
#2024
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
|
/ok to test |
dagardner-nv
approved these changes
Oct 30, 2024
|
/ok to test |
|
/ok to test |
|
/ok to test |
…github.com:yczhang-nv/Morpheus into fix-log-parsing-example-pipeline-null-output-issue
|
/ok to test |
|
/merge |
rapids-bot
bot
merged commit de72aaf
into
nv-morpheus:branch-24.10
10 of 11 checks passed
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Outdated suggestions cannot be applied.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.
Description
This bug is caused by the transition from
MultiMessagetoControlMessage.inference_stage.py::InferenceStage::_build_singlecalls_convert_one_responsein a loop for a batch, and the argument is passing is the same for the whole batch, but inside_convert_one_responsewe're grabbing the tensors and assigning starting at zero, so the tensors are overwriting each other and causes the issue.Added
batch_offsetvariable to keep track where the next incoming tensor should start writing to the output message.Closes #2019
By Submitting this PR I confirm: