phase 4

core/gpu/run.sh

@@ -0,0 +1,54 @@
+#!/bin/bash
+# Run the inference server
+#
+# Usage:
+#   ./run.sh                  # Local (pip install -r requirements.txt first)
+#   ./run.sh docker           # Docker (CPU)
+#   ./run.sh docker-gpu       # Docker with GPU
+#   ./run.sh stop             # Stop Docker container
+
+set -e
+cd "$(dirname "${BASH_SOURCE[0]}")"
+
+# Load env (create from template if missing)
+if [ ! -f .env ]; then
+    if [ -f .env.template ]; then
+        cp .env.template .env
+        echo "Created .env from template — edit as needed"
+    fi
+fi
+
+if [ -f .env ]; then
+    set -a
+    source .env
+    set +a
+fi
+
+case "${1:-local}" in
+    local)
+        python server.py
+        ;;
+    docker)
+        docker build -t mpr-inference .
+        ENV_FLAG=""; [ -f .env ] && ENV_FLAG="--env-file .env"
+        docker run --rm -p "${PORT:-8000}:8000" \
+            $ENV_FLAG \
+            --name mpr-inference \
+            mpr-inference
+        ;;
+    docker-gpu)
+        docker build -t mpr-inference .
+        ENV_FLAG=""; [ -f .env ] && ENV_FLAG="--env-file .env"
+        docker run --rm --gpus all -p "${PORT:-8000}:8000" \
+            $ENV_FLAG \
+            --name mpr-inference \
+            mpr-inference
+        ;;
+    stop)
+        docker stop mpr-inference 2>/dev/null || true
+        ;;
+    *)
+        echo "Usage: ./run.sh [local|docker|docker-gpu|stop]"
+        exit 1
+        ;;
+esac