Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Add support for response sender in the default mode #364

Merged
merged 7 commits into from
Jun 6, 2024

Conversation

kthui
Copy link
Contributor

@kthui kthui commented Jun 1, 2024

Related PR: triton-inference-server/server#7311

Add support for non-decoupled models to use response sender. Removed the non-decoupled data pipeline.

Items to be done on another ticket:

  • Re-implement restart functionality to the decoupled data pipeline. [This functionality is never mentioned on documentation, so it is ok to skip it for now]

Logistics:

  • All commits on this PR came from previously approved PRs (less copyright/documentation updates), the purpose of this PR is to merge the feature into the main branch.

kthui added 4 commits May 31, 2024 15:11
…360)

* Add response sender to non-decoupled model and unify data pipelines

* Rename variable and class name
* Fix decoupled gpu output error handling

* Return full error string upon exception from model
* Response sender to check for improper non-decoupled model usage

* Force close response sender on exception

* Rename functions
src/python_be.cc Outdated Show resolved Hide resolved
@kthui kthui requested review from krishung5 and Tabrizian June 5, 2024 01:28
@kthui kthui merged commit 27f04d1 into main Jun 6, 2024
3 checks passed
@kthui kthui deleted the jacky-res-sender-main branch June 6, 2024 00:54
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Development

Successfully merging this pull request may close these issues.

3 participants