Auto-update README with current k8s applications

Generated by CI/CD workflow on 2026-06-04 16:29:35 This PR updates the README.md file with the current list of applications found in the k8s/ directory structure.
2026-06-04 16:29:35 +00:00
2 changed files with 3 additions and 4 deletions
@@ -6,7 +6,7 @@ data:
  LLAMA_CACHE: /models
  LLAMA_ARG_HOST: 0.0.0.0
  LLAMA_ARG_PORT: "8080"
-  LLAMA_ARG_HF_REPO: "unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q6_K"
+  LLAMA_ARG_HF_REPO: unsloth/Qwen3.6-35B-A3B-MTP-GGUF:UD-Q6_K
  LLAMA_ARG_CTX_SIZE: "32768"
  LLAMA_ARG_FLASH_ATTN: auto
  LLAMA_ARG_FIT: "on"
@@ -18,7 +18,6 @@ spec:
      labels:
        app: llamacpp
    spec:
-      dnsPolicy: Default
      nodeSelector:
        kubernetes.io/hostname: ai.tail2fe2d.ts.net
      tolerations:
@@ -28,8 +27,8 @@ spec:
          effect: NoSchedule
      containers:
        - name: llamacpp
-          image: ghcr.io/ggml-org/llama.cpp:server-rocm-b9501 
-          imagePullPolicy: IfNotPresent
+          image: ghcr.io/ggml-org/llama.cpp:server-rocm
+          imagePullPolicy: Always
          envFrom:
            - configMapRef:
                name: llamacpp-config