llmopt-server / start.sh
Shrot101's picture
feat: initialize core LLMOpt framework including model routing, optimization engines, and frontend dashboard infrastructure.
bd238e9
raw
history blame contribute delete
291 Bytes
#!/bin/bash
# Start the LLMOpt FastAPI server (Gunicorn with Uvicorn workers for production)
echo "Starting LLMOpt Server for production..."
# Default to 7860 for Hugging Face Spaces
gunicorn llmopt.api.app:app -k uvicorn.workers.UvicornWorker --bind 0.0.0.0:7860 --workers 2 --timeout 120