[serve][llm] Enable KV cache offloading & KV routing awareness of CPU KV caches

[jeffreywang88]

Description

• Need to enable KB cache offloading generally for all routers

from ray.serve.config import RequestRouterConfig
from ray.serve.llm import LLMConfig
from ray.serve.llm.request_router import KVAwareRouter

llm_config = LLMConfig(
    model_loading_config={
        "model_id": "my-model",
        "model_source": "my-model",
    },
    deployment_config={
        "request_router_config": RequestRouterConfig(
            request_router_class=KVAwareRouter,
        ),
    },
    engine_kwargs={
        "enable_prefix_caching": True,
        "kv_offloading_backend": "native",
        "kv_offloading_size": 8,  # GiB of CPU cache per replica
    },
)

Observed KV cache offloading / reloading, and I'll add grafana dashboards for KV cache offloading observability in a follow-up.

• Workload characteristic: A two-replica Ray Serve LLM workload on L4s using Qwen3-0.6B with native KV offload, capped GPU KV cache, sticky session routing, long repeated prompts, forced prefix-cache resets, and same-session follow-ups.

Related issues

Link related issues: "Fixes #1234", "Closes #1234", or "Related to #1234".

Additional information

Optional: Add implementation details, API changes, usage examples, screenshots, etc.