Update README.md

README.md

@@ -312,7 +312,12 @@ VLLM_DISABLE_COMPILE_CACHE=1 python benchmarks/benchmark_latency.py --input-len
 
 We benchmarked the throughput in a serving environment.
 
-Download sharegpt dataset: `wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json`
+Download sharegpt dataset:
+
+```Shell
+wget https://huggingface.co/datasets/anon8231489123/ShareGPT_Vicuna_unfiltered/resolve/main/ShareGPT_V3_unfiltered_cleaned_split.json
+```
+
 Other datasets can be found in: https://github.com/vllm-project/vllm/tree/main/benchmarks
 
 Note: you can change the number of prompts to be benchmarked with `--num-prompts` argument for `benchmark_serving` script.