Example file for docker compose and k8s (#1006)

docker/compose.yaml

@@ -0,0 +1,31 @@
+services:
+  sglang:
+    image: lmsysorg/sglang:latest
+    container_name: sglang
+    volumes:
+      - ${HOME}/.cache/huggingface:/root/.cache/huggingface
+    restart: always
+    network_mode: host
+    # Or you can only publish port 30000
+    # ports:
+    #   - 30000:30000
+    environment:
+      HF_TOKEN: <secret>
+    entrypoint: python3 -m sglang.launch_server
+    command:
+      --model-path meta-llama/Meta-Llama-3.1-8B-Instruct
+      --host 0.0.0.0
+      --port 30000
+    ulimits:
+      memlock: -1
+      stack: 67108864
+    ipc: host
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"]
+    deploy:
+      resources:
+        reservations:
+          devices:
+            - driver: nvidia
+              device_ids: ['0']
+              capabilities: [gpu]