chore(deps): update ghcr.io/ggml-org/llama.cpp docker tag to v8660 (#1146)

Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>

Author: renovate[bot]

my-apps/ai/llama-cpp/deployment.yaml

@@ -33,7 +33,7 @@ spec:
         fsGroupChangePolicy: "OnRootMismatch"
       containers:
         - name: llama-cpp-server
-          image: ghcr.io/ggml-org/llama.cpp:server-cuda-b8589
+          image: ghcr.io/ggml-org/llama.cpp:server-cuda-b8660
           imagePullPolicy: IfNotPresent
           command: ["/app/llama-server"]
           args: