Update README.md

README.md

@@ -349,13 +349,13 @@ Run the benchmarks under `vllm` root folder:
 ### baseline
 ```Shell
 export MODEL=Qwen/Qwen3-8B
-python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model $MODEL --batch-size 1
+vllm bench latency --input-len 256 --output-len 256 --model $MODEL --batch-size 1
 ```
 
 ### AWQ-INT4
 ```Shell
 export MODEL=pytorch/Qwen3-8B-AWQ-INT4
-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
 ```
 
 ## benchmark_serving