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

tgis-standalone/caikit-standalone manifests #186

Merged

Conversation

dtrifiro
Copy link
Contributor

@dtrifiro dtrifiro commented Dec 22, 2023

Copy link
Contributor

openshift-ci bot commented Dec 22, 2023

Skipping CI for Draft Pull Request.
If you want CI signal for your change, please convert it to an actual PR.
You can still manually trigger a test run with /test all

}
....
```
- http only. Perform inference with HTTP. This example uses cURL.
Copy link
Contributor Author

@dtrifiro dtrifiro Dec 22, 2023

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Apart from this line, everything in the diff block below below hasn't really changed, only the level of indentation has.

@dtrifiro dtrifiro marked this pull request as ready for review December 22, 2023 11:56
- **[Text Generation Inference Server (TGIS)](https://github.com/opendatahub-io/text-generation-inference)**: Runtime that loads the models and provides the inference engine.
- **[KServe](https://github.com/opendatahub-io/kserve)**: A Kubernetes Custom Resource Definition that orchestrates model serving for all types of models. It includes serving runtimes that implement the loading of given types of model servers. KServe handles the lifecycle of the deployment object, storage access, and networking setup.
- **[Service Mesh](https://docs.openshift.com/container-platform/4.13/service_mesh/v2x/ossm-architecture.html)** (istio): The service mesh networking layer that manages traffic flows and enforces access policies.
- **[Serverless](https://docs.openshift.com/serverless/1.29/about/about-serverless.html)** (knative): A cloud-native development model that allows for serverless deployments of data models.

## Architecture of the stack

![KServe+Knative+Istio+Caikit_TGIS Diagram](https://github.com/opendatahub-io/caikit-tgis-serving/assets/8479010/7009b95d-0f6f-4f18-b0e6-355f360a5ad1)
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@heyselbi I see you're the last person to have updated this diagram. Do you think we should update it once again to reflect the new architecture?

name: caikit
containers:
- name: kserve-container
image: quay.io/opendatahub/caikit-nlp:stable
Copy link
Contributor Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This image isn't available (yet). Waiting on openshift/release#46641 for the workflows required to push the image on quay and the creation of a release branch on https://github.com/opendatahub-io/caikit-nlp

@Xaenalt
Copy link
Member

Xaenalt commented Jan 3, 2024

Overall lgtm, once openshift/release#46641 merges then will be good to merge

@dtrifiro

This comment was marked as outdated.

@dtrifiro dtrifiro marked this pull request as ready for review January 10, 2024 11:43
@openshift-ci openshift-ci bot requested a review from Jooho January 10, 2024 11:44
@dtrifiro dtrifiro changed the title Caikit standalone manifests tgis-standalone/caikit-standalone manifests Jan 11, 2024
This was referenced Jan 11, 2024
args:
- "--model-name=/mnt/models/"
args:
- "--model-name=/mnt/models/<model>"
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think we should remove <model>. I tried on my side, and it fails with it

@dtrifiro dtrifiro force-pushed the caikit-standalone-manifests branch 2 times, most recently from db52ea8 to 0ec7d54 Compare January 12, 2024 09:18
@dtrifiro
Copy link
Contributor Author

/retest

@Xaenalt
Copy link
Member

Xaenalt commented Jan 17, 2024

/lgtm
/approve

Copy link
Contributor

openshift-ci bot commented Jan 17, 2024

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: dtrifiro, Xaenalt

The full list of commands accepted by this bot can be found here.

The pull request process is described here

Needs approval from an approver in each of these files:

Approvers can indicate their approval by writing /approve in a comment
Approvers can cancel approval by writing /approve cancel in a comment

@openshift-merge-bot openshift-merge-bot bot merged commit 7746354 into opendatahub-io:main Jan 17, 2024
3 checks passed
@dtrifiro dtrifiro deleted the caikit-standalone-manifests branch January 17, 2024 15:43
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants