predxpramad/qwen-api repository overview

This image provides a ready-to-use deployment of the Qwen2.5-1.5B-Instruct model as a REST API service. It uses FastAPI for serving endpoints and leverages PyTorch with CUDA for GPU-accelerated inference. The container ensures reproducible environments, easy setup, and seamless deployment across systems. Users can run the container with GPU support to achieve faster inference and interact with the model through /chat endpoints. This setup is suitable for AI-powered applications, microservices, and DevOps-based ML deployments.

⁠Steps to Deploy

1. Pull the image

docker pull predxpramad/qwen-api

1. Run the container (GPU)

docker run --gpus all -p 8000:8000 predxpramad/qwen-api

1. Access API Open:

http://localhost:8000/docs

1. Test endpoint

{
  "prompt": "Explain Docker in simple terms"
}