# SPDX-FileCopyrightText: Copyright 2026 SAP SE or an SAP affiliate company and cobaltcore-dev contributors
# SPDX-License-Identifier: Apache-2.0

apiVersion: thalamus.cloud/v1alpha1
kind: Model
metadata:
  name: qwen3-6-27b
  namespace: thalamus
spec:
  backend: native
  serving:
    engine:
      image: docker.io/vllm/vllm-openai:v0.26.0
      args:
        - --gpu-memory-utilization=0.95
        - --tensor-parallel-size=1
        - --reasoning-parser=qwen3
        - --tool-call-parser=qwen3_coder
        - --enable-auto-tool-choice
        - '--speculative-config={"method": "mtp", "num_speculative_tokens": 2}'
      resources:
        requests:
          cpu: "4"
          memory: 16Gi
          nvidia.com/gpu: "1"
        limits:
          cpu: "8"
          memory: 32Gi
          nvidia.com/gpu: "1"
    epp:
      image: ghcr.io/llm-d/llm-d-router-endpoint-picker:v0.9.0
      resources:
        requests:
          cpu: 100m
          memory: 256Mi
        limits:
          cpu: 200m
          memory: 512Mi
  weights:
    type: hf
    hf:
      repoId: Qwen/Qwen3.6-27B
      tokenSecret:
        name: hf-token
        key: HF_TOKEN