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.

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 @@ class StackRun(Subcommand):
         )
 
     def _run_stack_run_cmd(self, args: argparse.Namespace) -> None:
-        from pathlib import Path
-
         import pkg_resources
         import yaml
 
@@ -66,19 +67,27 @@ class StackRun(Subcommand):
             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 @@ class StackRun(Subcommand):
             )
             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)