From cff4c6dfe5b66699c2d84a755fdc33d81822f926 Mon Sep 17 00:00:00 2001 From: Nir Rozenbaum Date: Thu, 4 Dec 2025 20:03:22 +0200 Subject: [PATCH] chore: update released quickstart to v1.2.1 Signed-off-by: Nir Rozenbaum --- site-src/guides/index.md | 46 ++++++++++++++++++++-------------------- 1 file changed, 23 insertions(+), 23 deletions(-) diff --git a/site-src/guides/index.md b/site-src/guides/index.md index dfca410e9..c046168c4 100644 --- a/site-src/guides/index.md +++ b/site-src/guides/index.md @@ -18,25 +18,25 @@ ```bash kubectl create secret generic hf-token --from-literal=token=$HF_TOKEN # Your Hugging Face Token with access to the set of Llama models - kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/vllm/gpu-deployment.yaml + kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/vllm/gpu-deployment.yaml ``` --8<-- "site-src/_includes/model-server-cpu.md" ```bash - kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/vllm/cpu-deployment.yaml + kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/vllm/cpu-deployment.yaml ``` --8<-- "site-src/_includes/model-server-sim.md" ```bash - kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/vllm/sim-deployment.yaml + kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/vllm/sim-deployment.yaml ``` ### Install the Inference Extension CRDs ```bash -kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.1.0/manifests.yaml +kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.2.1/manifests.yaml ``` ### Install the Gateway @@ -115,7 +115,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens Set the chart version and then select a tab to follow the provider-specific instructions. ```bash - export IGW_CHART_VERSION=v1.1.0 + export IGW_CHART_VERSION=v1.2.1 ``` --8<-- "site-src/_includes/epp.md" @@ -133,7 +133,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens 1. Deploy the Inference Gateway: ```bash - kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/gke/gateway.yaml + kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/gateway/gke/gateway.yaml ``` Confirm that the Gateway was assigned an IP address and reports a `Programmed=True` status: @@ -146,7 +146,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens 1. Deploy the HTTPRoute: ```bash - kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/gke/httproute.yaml + kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/gateway/gke/httproute.yaml ``` 1. Confirm that the HTTPRoute status conditions include `Accepted=True` and `ResolvedRefs=True`: @@ -195,7 +195,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens 1. Deploy the Inference Gateway: ```bash - kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/agentgateway/gateway.yaml + kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/gateway/agentgateway/gateway.yaml ``` Confirm that the Gateway was assigned an IP address and reports a `Programmed=True` status: @@ -206,7 +206,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens 1. Deploy the HTTPRoute: ```bash - kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/agentgateway/httproute.yaml + kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/gateway/agentgateway/httproute.yaml ``` 1. Confirm that the HTTPRoute status conditions include `Accepted=True` and `ResolvedRefs=True`: @@ -271,7 +271,7 @@ kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extens Deploy the sample InferenceObjective which allows you to specify priority of requests. ```bash - kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/inferenceobjective.yaml + kubectl apply -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/inferenceobjective.yaml ``` --8<-- "site-src/_includes/test.md" @@ -293,17 +293,17 @@ You have now deployed a basic Inference Gateway with a simple routing strategy. ```bash helm uninstall vllm-llama3-8b-instruct - kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/inferenceobjective.yaml --ignore-not-found - kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/vllm/cpu-deployment.yaml --ignore-not-found - kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/vllm/gpu-deployment.yaml --ignore-not-found - kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/vllm/sim-deployment.yaml --ignore-not-found + kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/inferenceobjective.yaml --ignore-not-found + kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/vllm/cpu-deployment.yaml --ignore-not-found + kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/vllm/gpu-deployment.yaml --ignore-not-found + kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/vllm/sim-deployment.yaml --ignore-not-found kubectl delete secret hf-token --ignore-not-found ``` 1. Uninstall the Gateway API Inference Extension CRDs: ```bash - kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.1.0/manifests.yaml --ignore-not-found + kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/releases/download/v1.2.1/manifests.yaml --ignore-not-found ``` 1. Choose one of the following options to cleanup the Inference Gateway. @@ -311,17 +311,17 @@ You have now deployed a basic Inference Gateway with a simple routing strategy. === "GKE" ```bash - kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/gke/gateway.yaml --ignore-not-found - kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/gke/healthcheck.yaml --ignore-not-found - kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/gke/gcp-backend-policy.yaml --ignore-not-found - kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/gke/httproute.yaml --ignore-not-found + kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/gateway/gke/gateway.yaml --ignore-not-found + kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/gateway/gke/healthcheck.yaml --ignore-not-found + kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/gateway/gke/gcp-backend-policy.yaml --ignore-not-found + kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/gateway/gke/httproute.yaml --ignore-not-found ``` === "Istio" ```bash - kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/istio/gateway.yaml --ignore-not-found - kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/istio/httproute.yaml --ignore-not-found + kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/gateway/istio/gateway.yaml --ignore-not-found + kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/gateway/istio/httproute.yaml --ignore-not-found ``` The following steps assume you would like to clean up ALL Istio resources that were created in this quickstart guide. @@ -341,8 +341,8 @@ You have now deployed a basic Inference Gateway with a simple routing strategy. === "Kgateway" ```bash - kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/agentgateway/gateway.yaml --ignore-not-found - kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.1.0/config/manifests/gateway/agentgateway/httproute.yaml --ignore-not-found + kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/gateway/agentgateway/gateway.yaml --ignore-not-found + kubectl delete -f https://raw.githubusercontent.com/kubernetes-sigs/gateway-api-inference-extension/refs/tags/v1.2.1/config/manifests/gateway/agentgateway/httproute.yaml --ignore-not-found ``` The following steps assume you would like to cleanup ALL Kgateway resources that were created in this quickstart guide.