Update README.md

README.md

@@ -328,12 +328,12 @@ python benchmarks/benchmark_serving.py --backend vllm --dataset-name sharegpt --
 ### float8dq
 Server:
 ```Shell
-vllm serve pytorch/Phi-4-mini-instruct-float8dq --tokenizer microsoft/Phi-4-mini-instruct -O3
+VLLM_DISABLE_COMPILE_CACHE=1 vllm serve pytorch/Phi-4-mini-instruct-float8dq --tokenizer microsoft/Phi-4-mini-instruct -O3
 ```
 
 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 jerryzh168/phi4-mini-float8dq --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 jerryzh168/phi4-mini-float8dq --num-prompts 1
 ```
 
 # Disclaimer