[Runtime] GLM 5.2 FP8 multi node runtimes

[YouNeedCryDear]

What this PR does

Adds GLM 5.2 FP8 multi-node runtime configuration:

• Adds the vllm-glm-5-2-fp8-multi ClusterServingRuntime with an SMG router and vLLM leader/worker engine configuration.
• Registers the runtime in config/runtimes/kustomization.yaml.
• Adds a matching InferenceService sample for glm-5-2-fp8-multi.
• Adds the GLM-5.2-FP8 base model configuration.

Why we need it

Enables OME users to deploy GLM 5.2 FP8 on a multi-node topology with vLLM.

Fixes #

How to test

Not run locally; configuration-only PR submission.

Checklist

• Tests added/updated (if applicable)
• Docs updated (if applicable)
• make test passes locally