A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 15, 11:00 UTC
[bugfix] fix the wrong parser (#17958)
Signed-off-by: reidliu41 <reid201711@gmail.com> Co-authored-by: reidliu41 <reid201711@gmail.com>
Reid committed
May 12, 2025 at 12:58 UTC
ada50aa2952fd0a7c645d75c9db472030131ddc7
1 file changed
+3
-4
vllm/entrypoints/cli/collect_env.py
+3
-4
@@ -4,12 +4,11 @@ import argparse
4
5
from vllm.collect_env import main as collect_env_main
6
from vllm.entrypoints.cli.types import CLISubcommand
7
-from vllm.entrypoints.openai.cli_args import make_arg_parser
7
from vllm.utils import FlexibleArgumentParser
8
9
10
class CollectEnvSubcommand(CLISubcommand):
12
- """The `serve` subcommand for the vLLM CLI. """
11
+ """The `collect-env` subcommand for the vLLM CLI. """
12
13
def __init__(self):
14
self.name = "collect-env"
@@ -23,12 +22,12 @@ class CollectEnvSubcommand(CLISubcommand):
22
def subparser_init(
23
self,
24
subparsers: argparse._SubParsersAction) -> FlexibleArgumentParser:
26
- serve_parser = subparsers.add_parser(
25
+ collect_env_parser = subparsers.add_parser(
26
"collect-env",
27
help="Start collecting environment information.",
28
description="Start collecting environment information.",
29
usage="vllm collect-env")
31
- return make_arg_parser(serve_parser)
30
+ return collect_env_parser
31
32
33
def cmd_init() -> list[CLISubcommand]: