Update Dockerfile

Dockerfile

@@ -10,7 +10,12 @@ RUN pip show vllm
 RUN pip list
 
 # Step 10 — Start API server with a model from HF Hub
-CMD ["python", "-m", "vllm.entrypoints.openai.api_server", \
+# CMD ["python", "-m", "vllm.entrypoints.openai.api_server", \
+#      "--model", "unsloth/Llama-3.2-3B-bnb-4bit", \
+#      "--host", "0.0.0.0", \
+#      "--port", "7860"]
+
+CMD ["python", "-m", "vllm", "serve", \
      "--model", "unsloth/Llama-3.2-3B-bnb-4bit", \
      "--host", "0.0.0.0", \
      "--port", "7860"]