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

implement Open Inference Protocol endpoints #1942

Merged
merged 7 commits into from
Jun 13, 2024
Merged

implement Open Inference Protocol endpoints #1942

merged 7 commits into from
Jun 13, 2024

Conversation

drbh
Copy link
Collaborator

@drbh drbh commented May 23, 2024

This PR adds support for the Open Inference Protocol (V2 Inference Protocol) with the following routes

Endpoint Category Action Method Request Payload Response Payload
v2/models/[/versions/<model_version>]/infer Inference POST $inference_request $inference_response
v2/models/<model_name>[/versions/<model_version>] Model Metadata GET - $metadata_model_response
v2/health/ready Server Ready GET - $ready_server_response
v2/health/live Server Live GET - $live_server_response
v2 Server Metadata GET - $metadata_server_response
v2/models/<model_name>[/versions/]/ready Model Ready GET - -

docs: https://kserve.github.io/website/0.12/modelserving/data_plane/v2_protocol/#open-inference-protocol-v2-inference-protocol

note: server must be built with --features kserve

@drbh
Copy link
Collaborator Author

drbh commented May 27, 2024

this PR should be ready to merge, I was originally going to add unit tests before promoting from a draft PR however all meaningful changes are limited to new HTTP endpoints and new structs and currently we are not testing these things as unit tests. I will add tests for these additions in the repo that builds the container.

Please let me know if there are any tests I should add or changes I should make!

@drbh drbh marked this pull request as ready for review May 27, 2024 14:29
router/src/lib.rs Outdated Show resolved Hide resolved
router/src/server.rs Outdated Show resolved Hide resolved
router/src/server.rs Outdated Show resolved Hide resolved
@drbh drbh requested a review from Narsil May 28, 2024 17:04
@drbh drbh force-pushed the kserve-endpoints branch from 3986e4d to fc051d4 Compare June 5, 2024 16:07
@drbh drbh merged commit f433f1f into main Jun 13, 2024
8 checks passed
@drbh drbh deleted the kserve-endpoints branch June 13, 2024 16:51
@Narsil Narsil mentioned this pull request Jun 24, 2024
5 tasks
yuanwu2017 pushed a commit to yuanwu2017/tgi-gaudi that referenced this pull request Sep 26, 2024
* feat: add kserve feature and basic routes

* feat: implement infer endpoint wrapper around generate

* fix: refactor and improve types

* fix: improve infer and simplify

* fix: cleanup and improve api docs

* fix: refactor and encapsulate kserve feat in file

* fix: remove typos after rebase
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants