This repository was archived by the owner on May 15, 2025. It is now read-only.
File tree Expand file tree Collapse file tree 2 files changed +50
-0
lines changed Expand file tree Collapse file tree 2 files changed +50
-0
lines changed Original file line number Diff line number Diff line change 1+ apiVersion : gateway.networking.k8s.io/v1
2+ kind : HTTPRoute
3+ metadata :
4+ name : inference-route
5+ spec :
6+ parentRefs :
7+ - name : inference-gateway
8+ rules :
9+ - matches :
10+ - path :
11+ type : PathPrefix
12+ value : /v1
13+ backendRefs :
14+ - name : vllm-30801
15+ port : 30801
16+ - name : vllm-30802
17+ port : 30802
18+ - name : vllm-30802
19+ port : 30802
Original file line number Diff line number Diff line change 1+ # ------------------------------------------------------------------------------
2+ # Kubernetes In Docker (KIND) Environment
3+ #
4+ # This will deploy the full development stack on a KIND cluster:
5+ #
6+ # * Istio Control Plane
7+ # * VLLM Simulator
8+ # * Inference Gateway
9+ #
10+ # **Note**: The Sail Operator must be deployed first.
11+ #
12+ # This will expose the VLLM simulator via an HTTPRoute. You can access the
13+ # Gateway with a port-forward:
14+ #
15+ # $ kubectl port-forward service/inference-gateway-istio 8080:80
16+ #
17+ # And the requests can be made:
18+ #
19+ # $ curl -v -w '\n' -X POST -H 'Content-Type: application/json' \
20+ # -d '{"model":"model1","messages":[{"role":"user","content":"Hello!"}]}' \
21+ # http://localhost:8080/v1/chat/completions
22+ #
23+ # ------------------------------------------------------------------------------
24+ apiVersion : kustomize.config.k8s.io/v1beta1
25+ kind : Kustomization
26+
27+ resources :
28+ - ../../components/istio-control-plane/
29+ - ../../components/vllm-sim/
30+ - ../../components/inference-gateway/
31+ - httproutes.yaml
You can’t perform that action at this time.
0 commit comments