Add GPU resource request to ray_serve_vllm_vicuna13b_manifest_v27.yaml

[sfc-gh-jsummer]

spec:
  containers:
  - name: vllm
    image: <<repository_url>>/rayservevllmvicuna13b
    resources:
      requests:
        nvidia.com/gpu: 1
      limits:
        nvidia.com/gpu: 1
    volumeMounts:
    - name: dshm
      mountPath: /dev/shm
    env:
      HF_TOKEN: <<hf_token>>
      HF_MODEL: lmsys/vicuna-13b-v1.5-16k
    args:
      - python3
      - main.py
      - deploy_app
      - "--url=ray://spcs-ray-custom-head-service:10001"
  volumes:
  - name: dshm
    source: memory
    size: 10.16Gi
  endpoints:
  - name: api
    port: 8000
    public: true
  networkPolicyConfig:
    allowInternetEgress: true