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, 02:00 UTC
[Misc] Fix the error in the tip for the --lora-modules parameter (#12319)
Signed-off-by: wangerxiao <863579016@qq.com>
Robin committed
Jan 23, 2025 at 00:48 UTC
fc66dee76d9957eab8fdb9d138d1ebaa0fad4649
1 file changed
+1
-1
vllm/entrypoints/openai/cli_args.py
+1
-1
@@ -117,7 +117,7 @@ def make_arg_parser(parser: FlexibleArgumentParser) -> FlexibleArgumentParser:
117
"or JSON format. "
118
"Example (old format): ``'name=path'`` "
119
"Example (new format): "
120
- "``{\"name\": \"name\", \"local_path\": \"path\", "
120
+ "``{\"name\": \"name\", \"path\": \"lora_path\", "
121
"\"base_model_name\": \"id\"}``")
122
parser.add_argument(
123
"--prompt-adapters",