update application file

Dockerfile

@@ -1,8 +1,10 @@
-FROM vllm/vllm-openai:latest
+FROM ghcr.io/ggml-org/llama.cpp:server
+
+ADD https://huggingface.co/unsloth/gemma-3-4b-it-GGUF/resolve/main/gemma-3-4b-it-Q8_0.gguf gemma3-4b.gguf
 
 WORKDIR /app
 
 EXPOSE 7860
 
-ENTRYPOINT ["python3", "-m", "vllm.entrypoints.openai.api_server"]
-CMD ["--model", "google/gemma-3-4b-it", "--host", "0.0.0.0", "--port", "7860", "--trust-remote-code"]
+ENTRYPOINT ["/llama-server"]
+CMD ["-m", "/gemma3-4b.gguf", "--host", "0.0.0.0", "--port", "7860", "-n", "-1"]