[Frontend] improve vllm bench <bench_type> --help display (#20430)

Signed-off-by: reidliu41 <reid201711@gmail.com>

vllm/entrypoints/cli/benchmark/main.py

@@ -8,6 +8,8 @@ import typing
 
 from vllm.entrypoints.cli.benchmark.base import BenchmarkSubcommandBase
 from vllm.entrypoints.cli.types import CLISubcommand
+from vllm.entrypoints.utils import (VLLM_SUBCMD_PARSER_EPILOG,
+                                    show_filtered_argument_or_group_from_help)
 
 if typing.TYPE_CHECKING:
     from vllm.utils import FlexibleArgumentParser
@@ -45,6 +47,9 @@ class BenchmarkSubcommand(CLISubcommand):
             )
             cmd_subparser.set_defaults(dispatch_function=cmd_cls.cmd)
             cmd_cls.add_cli_args(cmd_subparser)
+            show_filtered_argument_or_group_from_help(cmd_subparser,
+                                                      ["bench", cmd_cls.name])
+            cmd_subparser.epilog = VLLM_SUBCMD_PARSER_EPILOG
         return bench_parser
 
 

vllm/entrypoints/cli/run_batch.py

@@ -60,7 +60,7 @@ class RunBatchSubcommand(CLISubcommand):
         )
         run_batch_parser = make_arg_parser(run_batch_parser)
         show_filtered_argument_or_group_from_help(run_batch_parser,
-                                                  "run-batch")
+                                                  ["run-batch"])
         run_batch_parser.epilog = VLLM_SUBCMD_PARSER_EPILOG
         return run_batch_parser
 

vllm/entrypoints/cli/serve.py

@@ -97,7 +97,7 @@ class ServeSubcommand(CLISubcommand):
             "https://docs.vllm.ai/en/latest/configuration/serve_args.html")
 
         serve_parser = make_arg_parser(serve_parser)
-        show_filtered_argument_or_group_from_help(serve_parser, "serve")
+        show_filtered_argument_or_group_from_help(serve_parser, ["serve"])
         serve_parser.epilog = VLLM_SUBCMD_PARSER_EPILOG
         return serve_parser
 

vllm/entrypoints/utils.py

 # SPDX-License-Identifier: Apache-2.0
 # SPDX-FileCopyrightText: Copyright contributors to the vLLM project
 
+import argparse
 import asyncio
 import functools
 import os
@@ -15,8 +16,8 @@ from vllm.logger import init_logger
 logger = init_logger(__name__)
 
 VLLM_SUBCMD_PARSER_EPILOG = (
-    "Tip: Use `vllm [serve|run-batch] --help=<keyword>` "
-    "to explore arguments from help.\n"
+    "Tip: Use `vllm [serve|run-batch|bench <bench_type>] "
+    "--help=<keyword>` to explore arguments from help.\n"
     "   - To view a argument group:     --help=ModelConfig\n"
     "   - To view a single argument:    --help=max-num-seqs\n"
     "   - To search by keyword:         --help=max\n"
@@ -178,13 +179,19 @@ def _validate_truncation_size(
     return truncate_prompt_tokens
 
 
-def show_filtered_argument_or_group_from_help(parser, subcommand_name):
+def show_filtered_argument_or_group_from_help(parser: argparse.ArgumentParser,
+                                              subcommand_name: list[str]):
     import sys
 
     # Only handle --help=<keyword> for the current subcommand.
     # Since subparser_init() runs for all subcommands during CLI setup,
     # we skip processing if the subcommand name is not in sys.argv.
-    if subcommand_name not in sys.argv:
+    # sys.argv[0] is the program name. The subcommand follows.
+    # e.g., for `vllm bench latency`,
+    # sys.argv is `['vllm', 'bench', 'latency', ...]`
+    # and subcommand_name is "bench latency".
+    if len(sys.argv) <= len(subcommand_name) or sys.argv[
+            1:1 + len(subcommand_name)] != subcommand_name:
         return
 
     for arg in sys.argv: