Fix llama.cpp image reference: use ghcr.io/ggml-org/llama.cpp:server-b8840 with digest

Apps/llama-server/README.md

@@ -2,6 +2,8 @@
 
 Local LLM inference server using llama.cpp. Serves GGUF models via OpenAI-compatible REST API.
 
+**Image**: `ghcr.io/ggml-org/llama.cpp:server-b8840` (CPU-only, AVX2/AVX512)
+
 ## Purpose
 
 - **Port**: 8080 (TCP)

Apps/llama-server/docker-compose.yaml

@@ -2,7 +2,7 @@ name: llama-server
 
 services:
   llama-server:
-    image: ghcr.io/ggerganov/llama.cpp:server
+    image: ghcr.io/ggml-org/llama.cpp:server-b8840@sha256:99d2554c4c8d5339649dde530056cf10771823d7cd983dbd0441da9c419976b1
     container_name: llama-server
     restart: unless-stopped
     environment: