feat: Add parameters support to InferResponse #394
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
20 tasks
kthui
force-pushed
the
jacky-py-res-param
branch
from
7b63cc9 to
c3a9c1b
Compare
rmccorm4
reviewed
Jan 24, 2025
rmccorm4
reviewed
Jan 24, 2025
rmccorm4
reviewed
Jan 24, 2025
rmccorm4
reviewed
Jan 24, 2025
* Infer response to track parameters * Add parameters to binding infer response * Rank parameters argument up among InferResponse constructor arguments * Add setting parameters to Triton response * Send response parameters only on non-error * Fix double declaration * Unify py dictionary parameters to json str
kthui
force-pushed
the
jacky-py-res-param
branch
from
c3a9c1b to
816d4ac
Compare
rmccorm4
reviewed
Jan 24, 2025
rmccorm4
reviewed
Jan 24, 2025
rmccorm4
reviewed
Jan 24, 2025
There was a problem hiding this comment.
General look&feel LGTM - left a couple questions. Mostly defer to @krishung5 for an expert opinion
|
Thanks Jacky! |
nnshah1
reviewed
Jan 29, 2025
| @@ -803,6 +803,9 @@ You can read more about the inference response parameters in the [parameters | |||
| extension](https://github.com/triton-inference-server/server/blob/main/docs/protocol/extension_parameters.md) | |||
| documentation. | |||
|
|
|||
| Inference response parameters is currently not supported on BLS inference | |||
There was a problem hiding this comment.
not sure this is clear ....
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Outdated suggestions cannot be applied.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?
Add support for setting response parameters in regular and decoupled Python backend model response(s).
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#7964
Where should the reviewer start?
Start with the test cases on the related server PR, and then
pb_stub.cc->infer_response.cc->python_be.cc.Test plan:
New tests are added to the related server PR.
Caveats:
Responses to BLS models are not populated with the response parameters, if any. (DLIS-7864)
Background
N/A
Related Issues: (use one of the action keywords Closes / Fixes / Resolves / Relates to)
N/A