hsliu
afe5c2692c
- Improve API server with better error handling and response formatting - Enhance CLI with additional options for DiT stages and configuration - Add comprehensive examples in examples/basic/ including: - API client with health checks and text generation - Docker setup and usage examples - Simple usage patterns for different scenarios - Add utility scripts for model downloading and Docker setup - Update documentation with implementation details and testing guidelines - Fix configuration validation issues in OmniLLM - Improve stage configuration handling for AR and DiT stages - Add proper error handling and fallback mechanisms Tested with Qwen3-0.6B model: - Server starts successfully on port 8000 - Health and info endpoints working correctly - Text generation with various parameters functioning - API client examples working as expected - CLI help and configuration options working properly
27 lines
734 B
Python
27 lines
734 B
Python
"""
|
|
CLI entry point for vLLM-omni that intercepts vLLM commands.
|
|
"""
|
|
|
|
import sys
|
|
import argparse
|
|
from typing import List, Optional
|
|
from vllm_omni.entrypoints.omni import OmniServeCommand
|
|
|
|
|
|
def main():
|
|
"""Main CLI entry point that intercepts vLLM commands."""
|
|
# Check if --omni flag is present
|
|
if "--omni" in sys.argv:
|
|
# Remove --omni flag and "serve" command, process with vLLM-omni
|
|
omni_args = [arg for arg in sys.argv[1:] if arg not in ["--omni", "serve"]]
|
|
omni_serve = OmniServeCommand()
|
|
omni_serve.run(omni_args)
|
|
else:
|
|
# Forward to original vLLM CLI
|
|
from vllm.entrypoints.cli.main import main as vllm_main
|
|
vllm_main()
|
|
|
|
|
|
if __name__ == "__main__":
|
|
main()
|