address comments, update output msg

llama_stack/cli/stack/build.py

@@ -118,6 +118,11 @@ class StackBuild(Subcommand):
                 f"You can now run `llama stack configure {build_config.name}`",
                 color="green",
             )
+        else:
+            cprint(
+                f"You can now run `docker run -it -p 5000:5000 llamastack-{build_config.name}` or `llama stack configure llamastack-{build_config.name}`",
+                color="green",
+            )
 
     def _run_template_list_cmd(self, args: argparse.Namespace) -> None:
         import json

llama_stack/distribution/build_container.sh

@@ -128,4 +128,4 @@ set -x
 $DOCKER_BINARY build $DOCKER_OPTS -t $image_name -f "$TEMP_DIR/Dockerfile" "$REPO_DIR" $mounts
 set +x
 
-echo "Success! You can run it with: $DOCKER_BINARY run -p 8000:8000 $image_name"
+echo "Success! You can run it with: $DOCKER_BINARY $DOCKER_OPTS run -p 5000:5000 $image_name"

llama_stack/distribution/configure_container.sh

@@ -37,4 +37,6 @@ $DOCKER_BINARY run $DOCKER_OPTS -it \
   $docker_image \
   "stack" \
   "configure" \
-  "./llamastack-build.yaml"
+  "./llamastack-build.yaml" \
+  "--output-dir" \
+  "$container_build_dir"

llama_stack/distribution/server/server.py

@@ -409,7 +409,7 @@ async def resolve_impls_with_routing(run_config: StackRunConfig) -> Dict[Api, An
 
 
 def main(
-    yaml_config: str = "./llamastack-run.yaml",
+    yaml_config: str = "llamastack-run.yaml",
     port: int = 5000,
     disable_ipv6: bool = False,
 ):

llama_stack/distribution/templates/docker/llamastack-local-gpu/build.yaml

@@ -0,0 +1,11 @@
+name: local-gpu
+distribution_spec:
+  description: local meta reference
+  docker_image: null
+  providers:
+    inference: meta-reference
+    safety: meta-reference
+    agents: meta-reference
+    memory: meta-reference
+    telemetry: meta-reference
+image_type: docker