fix: Models should filter outputs based on requested outputs #366
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
Tabrizian
reviewed
Jun 11, 2024
GuanLuo
approved these changes
Jun 11, 2024
GuanLuo
reviewed
Jun 11, 2024
Tabrizian
approved these changes
Jun 11, 2024
kthui
changed the title
rmccorm4
approved these changes
Jun 11, 2024
This was referenced Jun 12, 2024
20 tasks
rmccorm4
pushed a commit
that referenced
this pull request
Jun 14, 2024
* Prune non requested outputs from non-decoupled models * Prune non requested outputs from decoupled models * [chore] Remove redundant copy
nv-kmcgill53
pushed a commit
that referenced
this pull request
Jun 17, 2024
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Outdated suggestions cannot be applied.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.
What does the PR do?
Models on Python backend should filter outputs based on requested outputs from the client.
Checklist
<commit_type>: <Title>Commit Type:
Check the conventional commit type
box here and add the label to the github PR.
Related PRs:
triton-inference-server/server#7338
Where should the reviewer start?
N/A
Test plan:
Add additional tests to L0_backend_python to affirm the behavior of non-decoupled and decoupled models on filtering outputs from requested outputs.
Refer to the related server PR.
Caveats:
N/A
Background
The non-decoupled data pipeline previously does filter outputs based on requested output, so this PR essentially brings this behavior back after switching non-decoupled models to use decoupled data pipeline.
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)
N/A