Create Dockerfile

Dockerfile

@@ -0,0 +1,25 @@
+FROM ghcr.io/ggml-org/llama.cpp:full
+
+WORKDIR /app
+
+RUN apt update && apt install -y python3 python3-pip python3-venv
+RUN python3 -m venv /opt/venv
+ENV PATH="/opt/venv/bin:$PATH"
+
+RUN pip install -U pip huggingface_hub
+
+RUN python3 -c 'from huggingface_hub import hf_hub_download; \
+    repo="gijl/gemma-4-31B-it-GGUF"; \
+    hf_hub_download(repo_id=repo, filename="gemma-4-31B-it-UD-Q5_K_XL.gguf", local_dir="/app"); \
+    hf_hub_download(repo_id=repo, filename="mmproj-BF16.gguf", local_dir="/app")'
+
+CMD ["--server", \
+     "-m", "/app/gemma-4-31B-it-UD-Q5_K_XL.gguf", \
+     "--mmproj", "/app/mmproj-BF16.gguf", \
+     "--host", "0.0.0.0", \
+     "--port", "7860", \
+     "-t", "2", \
+     "--cache-type-k", "q8_0", \
+     "--cache-type-v", "iq4_nl", \
+     "-c", "128000", \
+     "-n", "38912"]