http-route.yaml

# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.

# NOTE: You can remove metadata.namespace if using kubectl apply -n
# The backendRefs.namespace field should match where your InferencePool is deployed
apiVersion: gateway.networking.k8s.io/v1
kind: HTTPRoute
metadata:
  name: qwen-agg-route
spec:
  parentRefs:
    - group: gateway.networking.k8s.io
      kind: Gateway
      name: inference-gateway
      namespace: my-model
  rules:
    - backendRefs:
        - group: inference.networking.k8s.io
          kind: InferencePool
          name: qwen-agg-pool
          port: 8000
          weight: 1
      matches:
        - path:
            type: PathPrefix
            value: /
      timeouts:
        request: 300s