Update Dockerfile

Dockerfile

@@ -36,5 +36,12 @@ RUN vllm -v
 # WORKDIR /workspace
 # ENTRYPOINT ["./start_server.sh"]
 
-RUN vllm serve unsloth/Llama-3.2-1B-bnb-4bit --host 0.0.0.0 --port 7860 --cpu-num-threads 2
+# RUN vllm serve unsloth/Llama-3.2-1B-bnb-4bit --host 0.0.0.0 --port 7860 --cpu-num-threads 2
 # CMD ["vllm serve unsloth/Llama-3.2-1B-bnb-4bit --host 0.0.0.0 --port 7860"]
+CMD python3 -u -m vllm.entrypoints.openai.api_server \
+    --model "unsloth/Llama-3.2-1B-bnb-4bit" \
+    --host 0.0.0.0 \
+    --port 7860 \
+    --tensor-parallel-size 1 \
+    --gpu-memory-utilization 0.0 \
+    --num-cpu-threads 2