Revert "[bench] Support common prefix len config (for decode-only bench)" (#31240)

Signed-off-by: Ming Yang <minos.future@gmail.com>

vllm/benchmarks/datasets.py

@@ -1847,7 +1847,6 @@ def get_samples(args, tokenizer: TokenizerLike) -> list[SampleRequest]:
                 random_seed=args.seed,
                 dataset_path=args.dataset_path,
                 disable_shuffle=args.disable_shuffle,
-                prefix_len=args.common_prefix_len,
             ).sample(
                 tokenizer=tokenizer,
                 num_requests=args.num_prompts,

vllm/benchmarks/serve.py

@@ -1281,12 +1281,6 @@ def add_cli_args(parser: argparse.ArgumentParser):
         help="Repetition penalty sampling parameter. Only has effect on "
         "openai-compatible backends.",
     )
-    sampling_group.add_argument(
-        "--common-prefix-len",
-        type=int,
-        default=None,
-        help="Common prefix length shared by all prompts (used by random dataset)",
-    )
 
     parser.add_argument(
         "--served-model-name",