NG: llamacpp on the ai node (Qwen3.8-27B) with the AMD GPU device plugin

Co-Authored-By: Claude <noreply@anthropic.com>

k8s-ng/apps/llamacpp/configmap.yaml

@@ -0,0 +1,17 @@
+apiVersion: v1
+kind: ConfigMap
+metadata:
+  name: llamacpp-config
+data:
+  LLAMA_CACHE: /models
+  LLAMA_ARG_HOST: 0.0.0.0
+  LLAMA_ARG_PORT: "8080"
+  # The model is chosen here: <hf-user>/<repo>:<quant>. It is downloaded into
+  # /models on first start; changing it restarts the pod (reloader).
+  LLAMA_ARG_HF_REPO: "unsloth/Qwen3.8-27B-GGUF:UD-Q6_K"
+  LLAMA_ARG_CTX_SIZE: "131072"
+  LLAMA_ARG_N_GPU_LAYERS: all
+  LLAMA_ARG_FLASH_ATTN: "on"
+  LLAMA_ARG_FIT: "on"
+  # Strix Halo: mmap-ed weights hang or corrupt on ROCm; read them directly.
+  LLAMA_ARG_LOAD_MODE: dio

k8s-ng/apps/llamacpp/deployment.yaml

@@ -0,0 +1,74 @@
+apiVersion: apps/v1
+kind: Deployment
+metadata:
+  name: llamacpp
+  annotations:
+    reloader.stakater.com/auto: "true"
+  labels:
+    app: llamacpp
+spec:
+  replicas: 1
+  strategy:
+    type: Recreate # one GPU, one pod
+  selector:
+    matchLabels:
+      app: llamacpp
+  template:
+    metadata:
+      labels:
+        app: llamacpp
+    spec:
+      dnsPolicy: Default
+      nodeSelector:
+        workload/ai: "true"
+      tolerations:
+        - key: workload
+          operator: Equal
+          value: ai
+          effect: NoSchedule
+      containers:
+        - name: llamacpp
+          image: ghcr.io/ggml-org/llama.cpp:server-rocm-b11434
+          imagePullPolicy: IfNotPresent
+          envFrom:
+            - configMapRef:
+                name: llamacpp-config
+          env:
+            - name: HF_TOKEN
+              valueFrom:
+                secretKeyRef:
+                  name: llamacpp-hf-token
+                  key: token
+                  optional: true
+            # hipBLASLt gives the biggest prompt-processing gain on ROCm 7.x.
+            - name: ROCBLAS_USE_HIPBLASLT
+              value: "1"
+          ports:
+            - name: http
+              containerPort: 8080
+              protocol: TCP
+          resources:
+            limits:
+              amd.com/gpu: 1
+          startupProbe:
+            httpGet:
+              path: /health
+              port: http
+            failureThreshold: 180 # first start downloads the model
+            periodSeconds: 10
+            timeoutSeconds: 5
+          readinessProbe:
+            httpGet:
+              path: /health
+              port: http
+            failureThreshold: 3
+            periodSeconds: 10
+            timeoutSeconds: 5
+          volumeMounts:
+            - name: models
+              mountPath: /models
+      volumes:
+        - name: models
+          hostPath:
+            path: /var/lib/llamacpp/models
+            type: DirectoryOrCreate

k8s-ng/apps/llamacpp/kustomization.yaml

@@ -0,0 +1,7 @@
+apiVersion: kustomize.config.k8s.io/v1beta1
+kind: Kustomization
+
+resources:
+  - configmap.yaml
+  - deployment.yaml
+  - service.yaml

k8s-ng/apps/llamacpp/service.yaml

@@ -0,0 +1,15 @@
+apiVersion: v1
+kind: Service
+metadata:
+  name: llamacpp
+  labels:
+    app: llamacpp
+spec:
+  type: ClusterIP
+  selector:
+    app: llamacpp
+  ports:
+    - name: http
+      port: 8080
+      targetPort: http
+      protocol: TCP