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, 06:00 UTC
[Misc] Correct broken docs link (#19553)
Signed-off-by: Zerohertz <ohg3417@gmail.com>
Hyogeun Oh (오효근) committed
Jun 13, 2025 at 14:27 UTC
bb4a0decef68159c68057404ac9ca338c9259397
1 file changed
+3
-4
vllm/entrypoints/cli/serve.py
+3
-4
@@ -95,10 +95,9 @@ class ServeSubcommand(CLISubcommand):
95
type=str,
96
default='',
97
required=False,
98
- help="Read CLI options from a config file."
99
- "Must be a YAML with the following options:"
100
- "https://docs.vllm.ai/en/latest/serving/openai_compatible_server.html#cli-reference"
101
- )
98
+ help="Read CLI options from a config file. "
99
+ "Must be a YAML with the following options: "
100
+ "https://docs.vllm.ai/en/latest/configuration/serve_args.html")
101
102
serve_parser = make_arg_parser(serve_parser)
103
show_filtered_argument_or_group_from_help(serve_parser, "serve")