Make run yaml optional so dockers can start with just --env (#492)

When running with dockers, the idea is that users be able to work purely
with the `llama stack` CLI. They should not need to know about the
existence of any YAMLs unless they need to. This PR enables it.

The docker command now doesn't need to volume mount a yaml and can
simply be:
```bash
docker run -v ~/.llama/:/root/.llama \
  --env A=a --env B=b
```

## Test Plan

Check with conda first (no regressions):
```bash
LLAMA_STACK_DIR=. llama stack build --template ollama
llama stack run ollama --port 5001

# server starts up correctly
```

Check with docker
```bash
# build the docker
LLAMA_STACK_DIR=. llama stack build --template ollama --image-type docker

export INFERENCE_MODEL="meta-llama/Llama-3.2-3B-Instruct"

docker run -it  -p 5001:5001 \
  -v ~/.llama:/root/.llama \
  -v $PWD:/app/llama-stack-source \
  localhost/distribution-ollama:dev \
  --port 5001 \
  --env INFERENCE_MODEL=$INFERENCE_MODEL \
  --env OLLAMA_URL=http://host.docker.internal:11434
```

Note that volume mounting to `/app/llama-stack-source` is only needed
because we built the docker with uncommitted source code.

Author: ashwinb

llama_stack/cli/stack/run.py

@@ -5,9 +5,12 @@
 # the root directory of this source tree.
 
 import argparse
+from pathlib import Path
 
 from llama_stack.cli.subcommand import Subcommand
 
+REPO_ROOT = Path(__file__).parent.parent.parent.parent
+
 
 class StackRun(Subcommand):
     def __init__(self, subparsers: argparse._SubParsersAction):
@@ -48,8 +51,6 @@ def _add_arguments(self):
         )
 
     def _run_stack_run_cmd(self, args: argparse.Namespace) -> None:
-        from pathlib import Path
-
         import pkg_resources
         import yaml
 
@@ -66,19 +67,27 @@ def _run_stack_run_cmd(self, args: argparse.Namespace) -> None:
             return
 
         config_file = Path(args.config)
-        if not config_file.exists() and not args.config.endswith(".yaml"):
+        has_yaml_suffix = args.config.endswith(".yaml")
+
+        if not config_file.exists() and not has_yaml_suffix:
+            # check if this is a template
+            config_file = (
+                Path(REPO_ROOT) / "llama_stack" / "templates" / args.config / "run.yaml"
+            )
+
+        if not config_file.exists() and not has_yaml_suffix:
             # check if it's a build config saved to conda dir
             config_file = Path(
                 BUILDS_BASE_DIR / ImageType.conda.value / f"{args.config}-run.yaml"
             )
 
-        if not config_file.exists() and not args.config.endswith(".yaml"):
+        if not config_file.exists() and not has_yaml_suffix:
             # check if it's a build config saved to docker dir
             config_file = Path(
                 BUILDS_BASE_DIR / ImageType.docker.value / f"{args.config}-run.yaml"
             )
 
-        if not config_file.exists() and not args.config.endswith(".yaml"):
+        if not config_file.exists() and not has_yaml_suffix:
             # check if it's a build config saved to ~/.llama dir
             config_file = Path(
                 DISTRIBS_BASE_DIR
@@ -92,6 +101,7 @@ def _run_stack_run_cmd(self, args: argparse.Namespace) -> None:
             )
             return
 
+        print(f"Using config file: {config_file}")
         config_dict = yaml.safe_load(config_file.read_text())
         config = parse_and_maybe_upgrade_config(config_dict)
 

llama_stack/distribution/build_container.sh

@@ -122,7 +122,7 @@ add_to_docker <<EOF
 # This would be good in production but for debugging flexibility lets not add it right now
 # We need a more solid production ready entrypoint.sh anyway
 #
-ENTRYPOINT ["python", "-m", "llama_stack.distribution.server.server"]
+ENTRYPOINT ["python", "-m", "llama_stack.distribution.server.server", "--template", "$build_name"]
 
 EOF
 

llama_stack/distribution/server/server.py

@@ -16,6 +16,7 @@
 import warnings
 
 from contextlib import asynccontextmanager
+from pathlib import Path
 from ssl import SSLError
 from typing import Any, Dict, Optional
 
@@ -49,6 +50,9 @@
 from .endpoints import get_all_api_endpoints
 
 
+REPO_ROOT = Path(__file__).parent.parent.parent.parent
+
+
 def warn_with_traceback(message, category, filename, lineno, file=None, line=None):
     log = file if hasattr(file, "write") else sys.stderr
     traceback.print_stack(file=log)
@@ -279,9 +283,12 @@ def main():
     parser = argparse.ArgumentParser(description="Start the LlamaStack server.")
     parser.add_argument(
         "--yaml-config",
-        default="llamastack-run.yaml",
         help="Path to YAML configuration file",
     )
+    parser.add_argument(
+        "--template",
+        help="One of the template names in llama_stack/templates (e.g., tgi, fireworks, remote-vllm, etc.)",
+    )
     parser.add_argument("--port", type=int, default=5000, help="Port to listen on")
     parser.add_argument(
         "--disable-ipv6", action="store_true", help="Whether to disable IPv6 support"
@@ -303,10 +310,29 @@ def main():
                 print(f"Error: {str(e)}")
                 sys.exit(1)
 
-    with open(args.yaml_config, "r") as fp:
+    if args.yaml_config:
+        # if the user provided a config file, use it, even if template was specified
+        config_file = Path(args.yaml_config)
+        if not config_file.exists():
+            raise ValueError(f"Config file {config_file} does not exist")
+        print(f"Using config file: {config_file}")
+    elif args.template:
+        config_file = (
+            Path(REPO_ROOT) / "llama_stack" / "templates" / args.template / "run.yaml"
+        )
+        if not config_file.exists():
+            raise ValueError(f"Template {args.template} does not exist")
+        print(f"Using template {args.template} config file: {config_file}")
+    else:
+        raise ValueError("Either --yaml-config or --template must be provided")
+
+    with open(config_file, "r") as fp:
         config = replace_env_vars(yaml.safe_load(fp))
         config = StackRunConfig(**config)
 
+    print("Run configuration:")
+    print(yaml.dump(config.model_dump(), indent=2))
+
     app = FastAPI()
 
     try: