diff --git a/.gitignore b/.gitignore
index d05cc85..9224a8c 100644
--- a/.gitignore
+++ b/.gitignore
@@ -15,6 +15,7 @@
 !/.gitattributes
 !/.dockerignore
 !/Dockerfile
+!/docker-compose.yml
 !/assets/**
 !/CONTRIBUTING.md
 !/LICENSE
diff --git a/README.md b/README.md
index d72d743..295b479 100644
--- a/README.md
+++ b/README.md
@@ -114,10 +114,18 @@ docker run --gpus all -p 8000:8000 astrai:latest \
 
 # Run with volume mount for data
 docker run --gpus all -v /path/to/data:/data -it astrai:latest
+
+# Docker Compose (GPU, default)
+docker compose up -d
+
+# Docker Compose (CPU only)
+docker compose --profile cpu up -d
 ```
 
 > **Note**: `--gpus all` is required for CUDA support. Without it, `torch.cuda.is_available()` will return `False`.
 
+> **Note**: `--gpus all` is required for CUDA support. Without it, `torch.cuda.is_available()` will return `False`.
+
 #### Start HTTP Server
 
 Start the inference server with OpenAI and Anthropic-compatible HTTP API:
diff --git a/assets/docs/README-zh-CN.md b/assets/docs/README-zh-CN.md
index 92f9e96..c0256f4 100644
--- a/assets/docs/README-zh-CN.md
+++ b/assets/docs/README-zh-CN.md
@@ -120,6 +120,12 @@ docker run --gpus all -p 8000:8000 astrai:latest \
 
 # 挂载数据卷
 docker run --gpus all -v /path/to/data:/data -it astrai:latest
+
+# Docker Compose（GPU，默认）
+docker compose up -d
+
+# Docker Compose（仅 CPU）
+docker compose --profile cpu up -d
 ```
 
 > **注意**: 必须使用 `--gpus all` 才能启用 CUDA 支持，否则 `torch.cuda.is_available()` 将返回 `False`。
diff --git a/docker-compose.yml b/docker-compose.yml
new file mode 100644
index 0000000..225bc5b
--- /dev/null
+++ b/docker-compose.yml
@@ -0,0 +1,42 @@
+services:
+  server:
+    build: .
+    image: astrai:latest
+    ports:
+      - "8000:8000"
+    volumes:
+      - ./params:/app/params:ro
+      - ./checkpoints:/app/checkpoints
+    command: python -m scripts.tools.server --port 8000 --device cuda
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              count: 1
+              capabilities: [gpu]
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 60s
+    restart: unless-stopped
+
+  server-cpu:
+    profiles: [cpu]
+    build: .
+    image: astrai:latest
+    ports:
+      - "8000:8000"
+    volumes:
+      - ./params:/app/params:ro
+      - ./checkpoints:/app/checkpoints
+    command: python -m scripts.tools.server --port 8000 --device cpu
+    healthcheck:
+      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
+      interval: 30s
+      timeout: 10s
+      retries: 3
+      start_period: 120s
+    restart: unless-stopped