@tduncan / Nvidia-Optimization-Stack-VLLM Mirror · read-only / commits / fc66dee76d
Fork 0

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",