Implement Inference Extension

[ciarams87]

Proposed changes

Problem: As a cluster operator managing traffic for generative models
I want to route prompt traffic within my cluster based on generative model request criteria
So that I can build a system to host multiple generative models.

Solution: Add Gateway API Inference Extension support

Ref: https://gateway-api-inference-extension.sigs.k8s.io/

Testing: Extensive manual testing, and conformance testing is enabled in the pipeline, and everything is passing

Closes #3644

Checklist

Before creating a PR, run through this checklist and mark each as complete.

• I have read the CONTRIBUTING doc
• I have added tests that prove my fix is effective or that my feature works
• I have checked that all unit tests pass after adding my changes
• I have updated necessary documentation
• I have rebased my branch onto main
• I will ensure my PR is targeting the main branch and pulling from my branch from my own fork

Release notes

If this PR introduces a change that affects users and needs to be mentioned in the release notes,
please add a brief note that summarizes the change.

Added Gateway API Inference Extension support 

[codecov]

Codecov Report

❌ Patch coverage is 85.87922% with 159 lines in your changes missing coverage. Please review.
✅ Project coverage is 86.59%. Comparing base (d1300f7) to head (3bdae01).
⚠️ Report is 1 commits behind head on main.

Files with missing lines	Patch %	Lines
cmd/gateway/endpoint_picker.go	72.29%	37 Missing and 4 partials ⚠️
internal/controller/state/conditions/conditions.go	0.00%	40 Missing ⚠️
internal/controller/manager.go	23.52%	13 Missing ⚠️
cmd/gateway/commands.go	47.61%	11 Missing ⚠️
internal/controller/status/status_setters.go	79.06%	6 Missing and 3 partials ⚠️
internal/framework/controller/resource.go	0.00%	9 Missing ⚠️
internal/controller/state/graph/backend_refs.go	95.26%	7 Missing and 1 partial ⚠️
internal/controller/nginx/config/servers.go	96.05%	4 Missing and 2 partials ⚠️
...ternal/controller/state/dataplane/configuration.go	77.77%	5 Missing and 1 partial ⚠️
internal/controller/status/prepare_requests.go	93.40%	4 Missing and 2 partials ⚠️
... and 3 more

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #4091      +/-   ##
==========================================
- Coverage   86.71%   86.59%   -0.12%     
==========================================
  Files         128      131       +3     
  Lines       16758    17788    +1030     
  Branches       62       74      +12     
==========================================
+ Hits        14531    15404     +873     
- Misses       2042     2185     +143     
- Partials      185      199      +14     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.

[salonichf5]

Did some manual testing for inference extension and with some other path based headers, query params and seemed to be fine.

Did not work with URLRewrite filter, is that expectation correct?

[salonichf5]

looks like the helm chart is failing

Also not sure what pipeline wants to do here. Do we just test by installing minimum args needed? or this should have inference flag to test with

  ct install --config .ct.yaml --namespace nginx-gateway --helm-extra-set-args="--set=nginxGateway.image.tag=pr-4091 \
  --set=nginx.image.repository=ghcr.io/nginx/nginx-gateway-fabric/nginx \
  --set=nginx.plus=false \
  --set=nginx.image.tag=pr-4091 \
  --set=nginxGateway.image.pullPolicy=Never \
  --set=nginx.image.pullPolicy=Never \
  --set=nginxGateway.productTelemetry.enable=false"

[bjee19]

lgtm if we can just get those helm tests working