chore: 🔨 Use the v0.3.0 llm-d-inference-sim image tag.

[yafengio]

As the title suggests, we use the v0.3.0(latest) sim image to take advantage of the latest features.

For example, the size of the mirror image, etc. (121MB -> 37.2MB)

[netlify]

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

Name	Link
🔨 Latest commit	cc14228
🔍 Latest deploy log	https://app.netlify.com/projects/gateway-api-inference-extension/deploys/68804bb7714126000848996a
😎 Deploy Preview	https://deploy-preview-1140--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 @yafengio. Thanks for your PR.

I'm waiting for a kubernetes-sigs 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.

[nirrozenbaum]

hi @yafengio,
thanks for this PR.
we were actually using latest tag already but it got broken last week when llm-d simulator had a release that broke our ci e2e test. please see here: #1112.

ideally we would like to use latest images when things are stable enough to do it.
last simulator release had breaking changes and I do expect this may be the case for the next few releases until things become more stable in the sim (there is an ongoing effort to align with vLLM on many things, like cmd-line args, etc).

until that happens, I think it would be better for us to bump sim version in a controlled manner..
last time I tried using latest sim and run the e2e tests, it failed :/.

can you update the sim version to v0.2 explicitly and make sure e2e-tests are passing?

[yafengio]

can you update the sim version to v0.2 explicitly and make sure e2e-tests are passing?

@nirrozenbaum Thank you for your reply.

I will try to solve it.

[nirrozenbaum]

/ok-to-test

adding this to allow ci to run e2e tests for this PR

[nirrozenbaum]

@yafengio hi, is there any update on this issue?

[yafengio]

@yafengio hi, is there any update on this issue?

Currently unable to upgrade to the latest version, but I noticed the sim repository has fixed some issues. I'll conduct a new round of testing as soon as possible.

[yafengio]

@nirrozenbaum hi, I adapted based on the latest llm-d-inference-sim image (v0.3.0), and all e2e tests passed.

Please have a review. Thx

Ran 2 of 2 Specs in 70.359 seconds
SUCCESS! -- 2 Passed | 0 Failed | 0 Pending | 0 Skipped
--- PASS: TestAPIs (70.36s)
PASS
ok      sigs.k8s.io/gateway-api-inference-extension/test/e2e/epp        70.376s

[nirrozenbaum]

@yafengio Looks great! Thanks!

/lgtm
/approve

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: nirrozenbaum, yafengio

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 [nirrozenbaum]

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