phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-24 21:29:53 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore: merge --config and --template in server.py (#2716)

Browse source 
# What does this PR do?
Part of #2696 

## Test Plan
Run `llama stack run starter`

Error:
```

myenv ❯ llama stack run starters
WARNING  2025-07-10 12:12:43,052 llama_stack.cli.stack.run:82 server: Conda detected. Using conda environment myenv for the run.
usage: llama stack run [-h] [--port PORT] [--image-name IMAGE_NAME] [--env KEY=VALUE]
                       [--image-type {conda,venv}] [--enable-ui]
                       [config | template]
llama stack run: error: Could not resolve config or template 'starters'.

Tried the following locations:
  1. As file path: /Users/erichuang/projects/llama-stack-git/starters
  2. As template: /Users/erichuang/projects/llama-stack-git/llama_stack/templates/starters/run.yaml
  3. As built distribution: (/Users/erichuang/.llama/distributions/llamastack-starters/starters-run.yaml, /Users/erichuang/.llama/distributions/starters/starters-run.yaml)

Available templates: dell, test-env, vllm-gpu, test-template, cerebras, openai-api-verification, sambanova, passthrough, direct-config, together, openai, fireworks, meta-reference-gpu, __pycache__, dev, ollama, watsonx, remote-vllm, llama_api, groq, dummy, oracle, nvidia, ci-tests, postgres-demo, test-stack, bedrock, starter, hf-serverless, hf-endpoint, tgi, open-benchmark, verification

Did you mean one of these templates?
  - starter
  - together
  - postgres-demo
```
This commit is contained in:
ehhuang 2025-07-21 13:19:27 -07:00 • committed by GitHub
parent 9a03526672
commit 0d7a90b8bc
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
7 changed files with 176 additions and 76 deletions
Download patch file Download diff file Expand all files Collapse all files

36
llama_stack/distribution/server/server.py
View file

@ -32,6 +32,7 @@ from openai import BadRequestError
from pydantic import BaseModel, ValidationError
from llama_stack.apis.common.responses import PaginatedResponse
from llama_stack.cli.utils import add_config_template_args
from llama_stack.distribution.access_control.access_control import AccessDeniedError
from llama_stack.distribution.datatypes import (
AuthenticationRequiredError,
@ -53,6 +54,7 @@ from llama_stack.distribution.stack import (
validate_env_pair,
)
from llama_stack.distribution.utils.config import redact_sensitive_fields
from llama_stack.distribution.utils.config_resolution import Mode, resolve_config_or_template
from llama_stack.distribution.utils.context import preserve_contexts_async_generator
from llama_stack.log import get_logger
from llama_stack.providers.datatypes import Api
@ -377,20 +379,8 @@ class ClientVersionMiddleware:
def main(args: argparse.Namespace | None = None):
"""Start the LlamaStack server."""
parser = argparse.ArgumentParser(description="Start the LlamaStack server.")
parser.add_argument(
"--yaml-config",
dest="config",
help="(Deprecated) Path to YAML configuration file - use --config instead",
)
parser.add_argument(
"--config",
dest="config",
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.)",
)
add_config_template_args(parser)
parser.add_argument(
"--port",
type=int,
@ -409,20 +399,7 @@ def main(args: argparse.Namespace | None = None):
if args is None:
args = parser.parse_args()
log_line = ""
if hasattr(args, "config") and args.config:
# if the user provided a config file, use it, even if template was specified
config_file = Path(args.config)
if not config_file.exists():
raise ValueError(f"Config file {config_file} does not exist")
log_line = f"Using config file: {config_file}"
elif hasattr(args, "template") and 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")
log_line = f"Using template {args.template} config file: {config_file}"
else:
raise ValueError("Either --config or --template must be provided")
config_file = resolve_config_or_template(args.config, Mode.RUN)
logger_config = None
with open(config_file) as fp:
@ -442,9 +419,6 @@ def main(args: argparse.Namespace | None = None):
config = replace_env_vars(config_contents)
config = StackRunConfig(**cast_image_name_to_string(config))
# now that the logger is initialized, print the line about which type of config we are using.
logger.info(log_line)
_log_run_config(run_config=config)
app = FastAPI(