style: lint code

src/vllm/README.md

@@ -30,14 +30,14 @@ Please modify the `.env` file as needed for your use case.
 This service requires NVIDIA GPU to run properly. Uncomment the GPU configuration in `docker-compose.yaml`:
 
 ```yaml
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              count: 1
-              capabilities: [gpu]
-    runtime: nvidia
+deploy:
+  resources:
+    reservations:
+      devices:
+        - driver: nvidia
+          count: 1
+          capabilities: [gpu]
+runtime: nvidia
 ```
 
 ## Usage
@@ -117,7 +117,7 @@ VLLM_MAX_MODEL_LEN=4096  # Support up to 4K tokens
 For larger models, increase shared memory:
 
 ```yaml
-shm_size: 8g  # Increase to 8GB
+shm_size: 8g # Increase to 8GB
 ```
 
 ## Notes

src/vllm/README.zh.md

@@ -30,14 +30,14 @@
 此服务需要 NVIDIA GPU 才能正常运行。在 `docker-compose.yaml` 中取消注释 GPU 配置：
 
 ```yaml
-    deploy:
-      resources:
-        reservations:
-          devices:
-            - driver: nvidia
-              count: 1
-              capabilities: [gpu]
-    runtime: nvidia
+deploy:
+  resources:
+    reservations:
+      devices:
+        - driver: nvidia
+          count: 1
+          capabilities: [gpu]
+runtime: nvidia
 ```
 
 ## 使用方法
@@ -117,7 +117,7 @@ VLLM_MAX_MODEL_LEN=4096  # 支持最多 4K tokens
 对于更大的模型，增加共享内存：
 
 ```yaml
-shm_size: 8g  # 增加到 8GB
+shm_size: 8g # 增加到 8GB
 ```
 
 ## 注意事项

src/vllm/docker-compose.yaml

@@ -4,14 +4,14 @@ x-defaults: &defaults
     driver: json-file
     options:
       max-size: 100m
-      max-file: "3"
+      max-file: '3'
 
 services:
   vllm:
     <<: *defaults
     image: ${GLOBAL_REGISTRY:-}vllm/vllm-openai:${VLLM_VERSION:-v0.13.0}
     ports:
-      - "${VLLM_PORT_OVERRIDE:-8000}:8000"
+      - '${VLLM_PORT_OVERRIDE:-8000}:8000'
     volumes:
       - vllm_models:/root/.cache/huggingface
     environment:
@@ -21,13 +21,13 @@ services:
       - --model
       - ${VLLM_MODEL:-facebook/opt-125m}
       - --host
-      - "0.0.0.0"
+      - 0.0.0.0
       - --port
-      - "8000"
+      - '8000'
       - --max-model-len
-      - "${VLLM_MAX_MODEL_LEN:-2048}"
+      - '${VLLM_MAX_MODEL_LEN:-2048}'
       - --gpu-memory-utilization
-      - "${VLLM_GPU_MEMORY_UTIL:-0.9}"
+      - '${VLLM_GPU_MEMORY_UTIL:-0.9}'
     deploy:
       resources:
         limits:
@@ -42,7 +42,7 @@ services:
               capabilities: [gpu]
     shm_size: 4g
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://localhost:8000/health"]
+      test: [CMD, curl, -f, 'http://localhost:8000/health']
       interval: 30s
       timeout: 10s
       retries: 3