Update compose.yaml

compose.yaml

@@ -2,6 +2,7 @@ services:
   vllm-legacy:
     image: vllm/vllm-openai:v0.4.0.post1
     container_name: vllm-legacy
+    restart: unless-stopped
     network_mode: host
     ipc: host
     shm_size: "32gb"
@@ -20,16 +21,15 @@ services:
     command:
       - >
         exec python3 -m vllm.entrypoints.openai.api_server
-        --model "$$MODEL_PATH"
-        --served-model-name "$$SERVED_NAME"
-        --host 0.0.0.0 --port "$LISTEN_PORT"
-        --tensor-parallel-size "$$TP_SIZE"
-        --dtype "$$DTYPE"
-        --max-model-len "$$MAX_MODEL_LEN"
-        --gpu-memory-utilization "$$GPU_MEM_UTIL"
-        --max-num-seqs "$$MAX_NUM_SEQS"
-        $$VLLM_EXTRA_ARGS
-    restart: "no"
+        --model ${MODEL_PATH}
+        --served-model-name ${SERVED_NAME}
+        --host 0.0.0.0 --port ${LISTEN_PORT}
+        --tensor-parallel-size ${TP_SIZE}
+        --dtype ${DTYPE}
+        --max-model-len ${MAX_MODEL_LEN}
+        --gpu-memory-utilization ${GPU_MEM_UTIL}
+        --max-num-seqs ${MAX_NUM_SEQS}
+        ${VLLM_EXTRA_ARGS}
 
 volumes:
     models: