Fix: Downgrade NTPOT metrics error to verbose info to reduce noise

[ycjiang50]

What type of PR is this?

/kind bug

What this PR does / why we need it:
This PR downgrades the log level of the error "Output token count must be positive for NTPOT calculation" from Error to V(logutil.VERBOSE).Info.

Currently, when a client performs a streaming request without explicitly setting stream_options: {"include_usage": true}, the vLLM backend (and likely others) does not return usage statistics (token counts) in the final chunk.

The EPP relies on Usage.CompletionTokens to calculate the Normalized Time Per Output Token (NTPOT) metric. When this usage data is missing (0 tokens), EPP logs an error for every single request, causing significant log noise. For example, when I was using inference-perf to run some benchmark, which doesn't specify stream_options, the epp logs were completely overwhelmed by this error, making it hard to see any other useful output.

Which issue(s) this PR fixes:

Fixes #

Does this PR introduce a user-facing change?:

NONE

[netlify]

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

Name	Link
🔨 Latest commit	74bc5f9
🔍 Latest deploy log	https://app.netlify.com/projects/gateway-api-inference-extension/deploys/69a4ef015e9de7000826c1bd
😎 Deploy Preview	https://deploy-preview-2435--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 @ycjiang50. 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.

Details

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.

[LukeAVanDrie]

Currently, when a client performs a streaming request without explicitly setting stream_options: {"include_usage": true}, the vLLM backend (and likely others) does not return usage statistics (token counts) in the final chunk.

If this is somewhat expected behavior, I wonder if we should even log this case. I noticed this while running and inference-perf too.

[ahg-g]

+1 to luke's comment, lets return early at the beginning of the func if the value is 0 or less

[ycjiang50]

Thanks. I've updated the pr.

[ahg-g]

/lgtm
/approve

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is APPROVED

This pull-request has been approved by: ahg-g, ycjiang50

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

The pull request process is described here

Details

Needs approval from an approver in each of these files:

• OWNERS [ahg-g]

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

[nirrozenbaum]

/ok-to-test