24 lines
437 B
Plaintext
24 lines
437 B
Plaintext
from vllm_omni.entrypoints.api_server import run_server
|
|
|
|
# Start the API server
|
|
vllm>=0.9.0
|
|
torch>=2.0.0
|
|
transformers>=4.30.0
|
|
numpy>=1.21.0
|
|
pillow>=8.0.0
|
|
opencv-python>=4.5.0
|
|
|
|
# API and serving
|
|
fastapi>=0.100.0
|
|
uvicorn>=0.20.0
|
|
pydantic>=2.0.0
|
|
gradio>=3.0.0
|
|
|
|
# Async and distributed computing
|
|
asyncio-mqtt>=0.11.0
|
|
ray>=2.0.0
|
|
|
|
# Optional: DiT acceleration modules
|
|
# xDiT # Uncomment when available
|
|
# Cache-DiT # Uncomment when available
|