framework desktop offline ai updates

active/device_framework_desktop/quadlets/llama-server.container

@@ -2,8 +2,8 @@
 Description=A Llama CPP Server Running GPT OSS 120b
 
 [Container]
-# Shared AI pod
-Pod=ai.pod
+# Shared AI internal pod
+Pod=ai-internal.pod
 
 # Image is built locally via podman build
 Image=localhost/llama-cpp-vulkan:latest
@@ -18,8 +18,6 @@ AddDevice=/dev/dri
 # Server command
 Exec=--port 8000 \
     -c 48000 \
-    -b 48000 \
-    -ub 500 \
     --perf \
     --n-gpu-layers all \
     --jinja \
@@ -27,7 +25,7 @@ Exec=--port 8000 \
     --models-dir /models
 
 # Health Check
-HealthCmd=CMD-SHELL curl --fail http://127.0.0.1:8000/props?model=gpt-oss-120b || exit 1
+HealthCmd=CMD-SHELL curl --fail http://127.0.0.1:8000/props || exit 1
 HealthInterval=10s
 HealthRetries=3
 HealthStartPeriod=10s