Create Dockerfile

Dockerfile

@@ -0,0 +1,21 @@
+# Start with the official openEuler vLLM CPU base image
+FROM openeuler/vllm-cpu:latest
+
+# Set the working directory
+WORKDIR /app
+
+# (Optional) Install any additional dependencies your model or application might need
+# Example: 
+# RUN yum install -y some-package
+
+# Copy your model files into the container (assuming they are in a 'model' directory in your context)
+# You might need to adjust this depending on how you're providing the model
+COPY ./model /app/model
+
+# Set the environment variable for Hugging Face token if you're using gated models
+# Replace <YOUR_HUGGINGFACE_TOKEN> with your actual token
+ENV HUGGING_FACE_HUB_TOKEN="<YOUR_HUGGINGFACE_TOKEN>" 
+
+# Command to run the vLLM OpenAI-compatible server with your model
+# Replace "your-model-name" with the actual model ID from Hugging Face
+CMD ["python", "-m", "vllm.entrypoints.openai.api_server", "--model", "your-model-name", "--host", "0.0.0.0", "--port", "8000"]