- Add comprehensive PRD, architecture design, and test design documents - Implement core modules: OmniLLM, AsyncOmniLLM, stage configurations - Add DiT scheduler and cache manager for diffusion models - Implement CLI integration with --omni flag support - Add API server and plugin system for vLLM integration - Create comprehensive test suite with fixtures - Update dependencies to vLLM 0.10.2 and PyTorch 2.8.0 - Add conda environment setup and package installation - Implement stage-based processing architecture - Add multimodal output processing capabilities This commit establishes the foundation for multi-modality models inference and serving with non-autoregressive structures.
27 lines
702 B
Python
27 lines
702 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 process with vLLM-omni
|
|
omni_args = [arg for arg in sys.argv[1:] if arg != "--omni"]
|
|
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()
|