[ZealSV]

test_recommendation_workflow_end_to_end's recommendation job, and the endpoint the test deploys from its top recommendation, now use ml.g7.2xlarge instead of ml.g5.2xlarge.

The JumpStart model, which the benchmark test deploys and the recommendation test builds, now uses ml.g6.2xlarge: JumpStart has no ml.g7 image configuration for it, and ml.g6.2xlarge gets the same serving image as ml.g5.2xlarge.

Issue #, if available:

Description of changes:

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

[papriwal]

Automated review of the recommender integ test change. One suggestion, inline below: the model builder now targets ml.g6.2xlarge while the recommendation job targets ml.g7.2xlarge, and nothing after the deploy confirms which of the two the endpoint runs on. The inline comment proposes an assertion on the endpoint config.

[papriwal]

LGTM! Thank you for your contribution!

[github-actions]

🤖 AI code review

This PR updates the AI inference recommender integ test to run on newer instance families: the JumpStart model builder now uses ml.g6.2xlarge and the recommendation job/endpoint use ml.g7.2xlarge. It also adds an assertion that the deployed endpoint config's production variant instance type matches the requested recommendation instance type. All three prior usages of the renamed INSTANCE_TYPE constant are correctly updated, and the change is self-consistent. No issues found.

_{Reviewed commit 3f0ecea. Automated review; verify before acting.}