Update README.md

README.md

@@ -333,12 +333,12 @@ Run the benchmarks under `vllm` root folder:
 
 ### baseline
 ```Shell
-python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model microsoft/Phi-4-mini-instruct --batch-size 1
+vllm bench latency --input-len 256 --output-len 256 --model microsoft/Phi-4-mini-instruct --batch-size 1
 ```
 
 ### FP8
 ```Shell
-VLLM_DISABLE_COMPILE_CACHE=1 python benchmarks/benchmark_latency.py --input-len 256 --output-len 256 --model pytorch/Phi-4-mini-instruct-FP8 --batch-size 1
+VLLM_DISABLE_COMPILE_CACHE=1 vllm bench latency --input-len 256 --output-len 256 --model pytorch/Phi-4-mini-instruct-FP8 --batch-size 1
 ```
 
 </details>