Update README.md

README.md

@@ -339,7 +339,7 @@ VLLM_DISABLE_COMPILE_CACHE=1 vllm serve pytorch/Phi-4-mini-instruct-int4wo-hqq -
 
 Client:
 ```Shell
-VLLM_DISABLE_COMPILE_CACHE=1 python benchmarks/benchmark_serving.py --backend vllm --dataset-name sharegpt --tokenizer microsoft/Phi-4-mini-instruct --dataset-path ./ShareGPT_V3_unfiltered_cleaned_split.json --model pytorch/Phi-4-mini-instruct-int4wo-hqq --num-prompts 1
+python benchmarks/benchmark_serving.py --backend vllm --dataset-name sharegpt --tokenizer microsoft/Phi-4-mini-instruct --dataset-path ./ShareGPT_V3_unfiltered_cleaned_split.json --model pytorch/Phi-4-mini-instruct-int4wo-hqq --num-prompts 1
 ```