Use container right now

ramalama run/serve right now require the container, it has the version
of llama.cpp that works.

Long-term we may be able to remove this.

Signed-off-by: Eric Curtin <ecurtin@redhat.com>

ci.sh

@@ -43,6 +43,11 @@ main() {
   ./ramalama list | grep tinyllama
   ./ramalama list | grep tiny-vicuna-1b
   ./ramalama list | grep NAME
+
+  if [ "$os" = "Linux" ]; then # no macos support for running/serving models yet
+    timeout 8 ./ramalama serve granite-code | grep -m1 -i listen
+  fi
+
 #  ramalama list | grep granite-code
 #  ramalama rm granite-code
 }

ramalama

@@ -342,6 +342,11 @@ def main(args):
     conman = select_container_manager()
     ramalama_store = get_ramalama_store()
 
+    if conman:
+        conman_args = [conman, "run", "--rm", "-it", "--security-opt=label=disable", f"-v{ramalama_store}:/var/lib/ramalama", f"-v{os.path.expanduser('~')}:{os.path.expanduser('~')}", "-v/tmp:/tmp",
+                       f"-v{__file__}:{__file__}", "quay.io/ramalama/ramalama:latest", __file__] + args
+        os.execvp(conman, conman_args)
+
     try:
         cmd = args.pop(0)
         funcDict[cmd](ramalama_store, args)