Manifest updates

[kaushikmitr]

This pull request includes several changes to Kubernetes manifests and configurations to update service names, deployment configurations, and role-based access controls.

Service and Deployment Configuration Updates:

• examples/poc/manifests/llmservice.yaml: Added a new LLMServerPool kind and updated the models section to include new model names and objectives. Updated the poolRef to use vllm-llama2-7b-pool. [1] [2]
• examples/poc/manifests/vllm/vllm-lora-deployment.yaml: Added a new Service for vllm-llama2-7b-pool and updated the Deployment configuration to use vllm-llama2-7b-pool with reduced replicas.
• examples/poc/manifests/vllm/vllm-lora-service.yaml: Removed the old Service configuration for vllm-lora.

Role-Based Access Control (RBAC) Updates:

• pkg/manifests/ext_proc.yaml: Added new ClusterRole and ClusterRoleBinding for pod read access. Updated the deployment arguments to use vllm-llama2-7b-pool and added a verbosity level. [1] [2] [3]

Gateway Configuration Updates:

• pkg/manifests/gateway.yaml: Updated the gateway and gateway class names to instance-gateway. [1] [2] [3]
• pkg/manifests/patch_policy.yaml: Updated the gateway name references in the patch policy to instance-gateway. [1] [2]

[liu-cong]

/lgtm

Thanks!

[ahg-g]

@kaushikmitr can you address @liu-cong comments pls on this one? all are minor.

[kaushikmitr]

done

[ahg-g]

/label tide/merge-method-squash

/lgtm
/approve

[k8s-ci-robot]

[APPROVALNOTIFIER] This PR is APPROVED

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

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 [ahg-g]

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