Update README.md

README.md

@@ -260,9 +260,8 @@ vllm serve Qwen/Qwen2.5-VL-72B-Instruct \
   --served-model-name "qwen-vl" \
   --tensor-parallel-size 4 \
   --gpu-memory-utilization 0.95 \
-  --max-model-len 4096 \
+  --max-model-len 32768 \
   --dtype bfloat16 \
-  --enforce-eager \
   --trust-remote-code \
   --port 8000