Gateway API Inference Extension

Gateway API Inference Extension#

kubernetes-sigs/gateway-api-inference-extension Github stars Github forks Language Last Tag Last commit

IGW_LATEST_RELEASE=$(curl -s https://api.github.com/repos/kubernetes-sigs/gateway-api-inference-extension/releases \
  | jq -r '.[] | select(.prerelease == false) | .tag_name' \
  | sort -V \
  | tail -n1)

# Your Hugging Face Token with access to the set of Llama models
kubectl create secret generic hf-token --from-literal=token=$HF_TOKEN

kubectl apply -f "https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/${IGW_LATEST_RELEASE}/config/manifests/vllm/gpu-deployment.yaml"


kubectl apply -f "https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/${IGW_LATEST_RELEASE}/manifests.yaml"

本文访问量

本站总访问量

本站总访客数