deploy qwen 3.8

llamacpp/deployment-qwen38-27b.yaml

@@ -0,0 +1,117 @@
+# Qwen3.8-27B with MTP speculative decoding served by llama.cpp.
+# The primary and draft GGUFs are downloaded by llama-server into the shared
+# persistent llama.cpp cache on the NUCBox Radeon 8060S.
+---
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llamacpp-qwen38-27b
+  namespace: llamacpp
+  labels:
+    app: llamacpp
+    model: qwen3.8-27b
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate
+  selector:
+    matchLabels:
+      app: llamacpp
+      model: qwen3.8-27b
+  template:
+    metadata:
+      labels:
+        app: llamacpp
+        model: qwen3.8-27b
+    spec:
+      nodeSelector:
+        kubernetes.io/arch: amd64
+        hardware: high-memory
+      containers:
+      - name: llama-server
+        image: ghcr.io/ggml-org/llama.cpp:server-vulkan
+        imagePullPolicy: IfNotPresent
+        args:
+        - -hf
+        - ggml-org/Qwen3.8-27B-GGUF:Q4_K_M
+        - -hfd
+        - ggml-org/Qwen3.8-27B-GGUF:Q4_0
+        - --spec-default
+        - --spec-type
+        - draft-mtp
+        - --ctx-size
+        - "196608"
+        - --cache-type-k
+        - q8_0
+        - --cache-type-v
+        - q8_0
+        - --reasoning-preserve
+        - --fit
+        - off
+        - --agent
+        - --chat-template-kwargs
+        - '{"reasoning_effort":"medium"}'
+        - --alias
+        - qwen3.8-27b
+        - --host
+        - 0.0.0.0
+        - --port
+        - "8080"
+        - --jinja
+        ports:
+        - name: http
+          containerPort: 8080
+        resources:
+          requests:
+            cpu: "1000m"
+            memory: 2Gi
+          limits:
+            cpu: "4000m"
+            memory: 24Gi
+        readinessProbe:
+          httpGet:
+            path: /health
+            port: 8080
+          initialDelaySeconds: 30
+          periodSeconds: 10
+          failureThreshold: 6
+        livenessProbe:
+          httpGet:
+            path: /health
+            port: 8080
+          initialDelaySeconds: 180
+          periodSeconds: 30
+          failureThreshold: 5
+        securityContext:
+          privileged: true
+        volumeMounts:
+        - name: models
+          mountPath: /root/.cache/llama.cpp
+        - name: dri
+          mountPath: /dev/dri
+      volumes:
+      - name: models
+        persistentVolumeClaim:
+          claimName: llamacpp-models
+      - name: dri
+        hostPath:
+          path: /dev/dri
+          type: Directory
+---
+apiVersion: v1
+kind: Service
+metadata:
+  name: llamacpp-qwen38-27b
+  namespace: llamacpp
+  labels:
+    app: llamacpp
+    model: qwen3.8-27b
+spec:
+  type: ClusterIP
+  selector:
+    app: llamacpp
+    model: qwen3.8-27b
+  ports:
+  - name: http
+    port: 80
+    targetPort: 8080