Add Dockerfile

Dockerfile

@@ -0,0 +1,31 @@
+FROM pytorch/pytorch:2.6.0-cuda12.4-cudnn9-runtime
+
+ENV DEBIAN_FRONTEND=noninteractive \
+    PYTHONUNBUFFERED=1 \
+    PYTHONDONTWRITEBYTECODE=1 \
+    PERSIST_ROOT=/app/data \
+    HF_HOME=/app/data/cache/huggingface \
+    TRANSFORMERS_CACHE=/app/data/cache/huggingface \
+    HF_HUB_ENABLE_HF_TRANSFER=1 \
+    TOKENIZERS_PARALLELISM=false \
+    PORT=7860
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+      build-essential ca-certificates cmake curl git wget && \
+    rm -rf /var/lib/apt/lists/*
+
+WORKDIR /app
+COPY requirements.txt .
+RUN python -m pip install --no-cache-dir --upgrade pip && \
+    python -m pip install --no-cache-dir -r requirements.txt
+
+# Pinned official llama.cpp revision for reproducible GGUF conversion.
+RUN git clone https://github.com/ggml-org/llama.cpp.git /opt/llama.cpp && \
+    cd /opt/llama.cpp && \
+    git checkout 4762ad7316dcdec20016ab5985fb46a27902204d && \
+    cmake -B build -DGGML_CUDA=OFF -DLLAMA_CURL=OFF -DCMAKE_BUILD_TYPE=Release && \
+    cmake --build build --config Release -j2 --target llama-quantize
+
+COPY . /app
+EXPOSE 7860
+CMD ["python", "app.py"]