Upload Dockerfile

Dockerfile

@@ -0,0 +1,39 @@
+FROM ubuntu:22.04
+
+# ── System deps ────────────────────────────────────────────────────────────
+ENV DEBIAN_FRONTEND=noninteractive
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        g++ make libgomp1 libgomp-10-dev \
+        python3 python3-pip python3-dev \
+        curl ca-certificates \
+    && rm -rf /var/lib/apt/lists/*
+
+# ── Python deps ────────────────────────────────────────────────────────────
+WORKDIR /app
+COPY requirements.txt .
+RUN pip3 install --no-cache-dir -r requirements.txt
+
+# ── Copy source and compile C++ inference binary ───────────────────────────
+COPY llama_inference.cpp .
+RUN g++ -O3 -march=native -fopenmp \
+        -o llama_inference llama_inference.cpp -lm \
+    && chmod +x llama_inference \
+    && echo "[OK] llama_inference compiled"
+
+# ── Copy app files ─────────────────────────────────────────────────────────
+COPY server.py .
+COPY index.html .
+
+# ── HF Spaces runs as non-root user 1000 ──────────────────────────────────
+RUN useradd -m -u 1000 user
+RUN mkdir -p /app/models && chown -R user:user /app
+USER user
+
+# HF Spaces requires port 7860
+EXPOSE 7860
+
+# Model repo — override via Space secret if needed
+ENV HF_MODEL_REPO="NOT-OMEGA/LLaMA"
+ENV PORT=7860
+
+CMD ["python3", "server.py"]