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 16, 08:15 UTC
[Doc] Fix typo error in vllm/entrypoints/openai/cli_args.py (#10196)
yansh97 committed
Nov 11, 2024 at 08:14 UTC
ad9a78bf640cca930de76a066a2f34139b9acb65
1 file changed
+1
-1
vllm/entrypoints/openai/cli_args.py
+1
-1
@@ -190,7 +190,7 @@ def make_arg_parser(parser: FlexibleArgumentParser) -> FlexibleArgumentParser:
190
default=False,
191
help=
192
"Enable auto tool choice for supported models. Use --tool-call-parser"
193
- "to specify which parser to use")
193
+ " to specify which parser to use")
194
195
valid_tool_parsers = ToolParserManager.tool_parsers.keys()
196
parser.add_argument(