SLO Aware Routing Plugins Only

[BenjaminBraunDev]

This is PR 2/3 for the SLO aware routing, containing all the new plugins required for scoring/routing, tracking, and profile picking (as well as their metrics, required for them to compile). Due to the size of the change, we aren't including integration in this PR, this is solely the addition of plugin files, with integration into EPP coming in PR 3. (Cut from full PR #1839)

The plugins, once implemented include the following features:

1. Profile picking based on request header (effectively a per-request feature flag)
2. Tracking requests and their latencies (via requestcontrol plugins), makes predictions during inference for verification, and sends data back to training sidecar for processing.
3. Routing via Scorer that uses the latency prediction sidecars to predict latencies for each pod based on its headroom.

Design and details: #1323

Does this PR introduce a user-facing change?:

NONE

[netlify]

✅ Deploy Preview for gateway-api-inference-extension ready!

Name	Link
🔨 Latest commit	177b932
🔍 Latest deploy log	https://app.netlify.com/projects/gateway-api-inference-extension/deploys/691cfc6d4dcceb0008ebfa18
😎 Deploy Preview	https://deploy-preview-1849--gateway-api-inference-extension.netlify.app
📱 Preview on mobile	Toggle QR Code... Use your smartphone camera to open QR code link.

---

To edit notification comments on pull requests, go to your Netlify project configuration.

[k8s-ci-robot]

Hi @BenjaminBraunDev. Thanks for your PR.

I'm waiting for a github.com member to verify that this patch is reasonable to test. If it is, they should reply with /ok-to-test on its own line. Until that is done, I will not automatically test new commits in this PR, but the usual testing commands by org members will still work. Regular contributors should join the org to skip this step.

Once the patch is verified, the new status will be reflected by the ok-to-test label.

I understand the commands that are listed here.

Instructions for interacting with me using PR comments are available here. If you have questions or suggestions related to my behavior, please file an issue against the kubernetes-sigs/prow repository.

[kfswain]

I think a lot of these helper functions are doing way too much in a single func, and we should unexport many of these helper funcs since they should all be in the same package.

Additionally I would like Jeff to take a look to see if we can emit metrics from a plugin without having to register them, as I don't want to set a precedent that metrics arent generalizable and pluggable.

/approve

Will LGTM after Jeff responds & the helper funcs are unexported. TY!

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: BenjaminBraunDev, kfswain

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:

• OWNERS [kfswain]

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

[BenjaminBraunDev]

I think a lot of these helper functions are doing way too much in a single func, and we should unexport many of these helper funcs since they should all be in the same package.

Additionally I would like Jeff to take a look to see if we can emit metrics from a plugin without having to register them, as I don't want to set a precedent that metrics arent generalizable and pluggable.

/approve

Will LGTM after Jeff responds & the helper funcs are unexported. TY!

Agree with this. I will unexport pretty much everything here as it's an artifact of when latency predictor wasn't in the plugin package. The helper functions can be broken down further. I will work on that.

[kfswain]

The helper functions can be broken down further. I will work on that.

SG, I don't consider that a blocker for this specific PR, but I think will be important for long term maintenance. So, up to you if you want to include in this PR or a follow up.

[kfswain]

/ok-to-test

[BenjaminBraunDev]

Reached out to @JeffLuoo regarding metric consolidation. Waiting on response there, but everything else should be ready to merge.