phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-01 16:24:44 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Make run yaml optional so dockers can start with just --env

Browse source
This commit is contained in:
Ashwin Bharambe 2024-11-20 11:56:08 -08:00
parent 1d8d0593af
commit adbb605a50
2 changed files with 28 additions and 3 deletions
Download patch file Download diff file Expand all files Collapse all files

2
llama_stack/distribution/build_container.sh
View file

@ -122,7 +122,7 @@ add_to_docker <<EOF
# This would be good in production but for debugging flexibility lets not add it right now # 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 # 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 EOF

29
llama_stack/distribution/server/server.py
View file

@ -16,6 +16,7 @@ import traceback
import warnings import warnings
from contextlib import asynccontextmanager from contextlib import asynccontextmanager
from pathlib import Path
from ssl import SSLError from ssl import SSLError
from typing import Any, Dict, Optional from typing import Any, Dict, Optional
@ -49,6 +50,9 @@ from llama_stack.distribution.stack import (
from .endpoints import get_all_api_endpoints 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): def warn_with_traceback(message, category, filename, lineno, file=None, line=None):
log = file if hasattr(file, "write") else sys.stderr log = file if hasattr(file, "write") else sys.stderr
traceback.print_stack(file=log) traceback.print_stack(file=log)
@ -279,9 +283,12 @@ def main():
parser = argparse.ArgumentParser(description="Start the LlamaStack server.") parser = argparse.ArgumentParser(description="Start the LlamaStack server.")
parser.add_argument( parser.add_argument(
"--yaml-config", "--yaml-config",
default="llamastack-run.yaml",
help="Path to YAML configuration file", 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("--port", type=int, default=5000, help="Port to listen on")
parser.add_argument( parser.add_argument(
"--disable-ipv6", action="store_true", help="Whether to disable IPv6 support" "--disable-ipv6", action="store_true", help="Whether to disable IPv6 support"
@ -303,10 +310,28 @@ def main():
print(f"Error: {str(e)}") print(f"Error: {str(e)}")
sys.exit(1) 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")
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")
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 = replace_env_vars(yaml.safe_load(fp))
config = StackRunConfig(**config) config = StackRunConfig(**config)
print(f"Using config file: {config_file}")
print(f"Config: {yaml.dump(config.model_dump(), indent=2)}")
app = FastAPI() app = FastAPI()
try: try: