Update README.md

README.md

@@ -255,7 +255,7 @@ pip install fbgemm-gpu-genai
 
 ```Shell
 export MODEL=Qwen/Qwen3-32B # or pytorch/Qwen3-32B-FP8
-VLLM_DISABLE_COMPILE_CACHE=1 python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model $MODEL --batch-size 1
+VLLM_DISABLE_COMPILE_CACHE=1 vllm bench latency --input-len 256 --output-len 256 --model $MODEL --batch-size 1
 ```
 </details>