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, 07:15 UTC
[bugfix] small fix logic issue (#18999)
Signed-off-by: reidliu41 <reid201711@gmail.com> Co-authored-by: reidliu41 <reid201711@gmail.com>
Reid committed
Jun 3, 2025 at 13:35 UTC
17430e36531aeade52518b13961706d4227310f9
1 file changed
+1
-1
vllm/engine/arg_utils.py
+1
-1
@@ -455,7 +455,7 @@ class EngineArgs:
455
title="ModelConfig",
456
description=ModelConfig.__doc__,
457
)
458
- if 'serve' not in sys.argv[1:] and '--help' not in sys.argv[1:]:
458
+ if not ('serve' in sys.argv[1:] and '--help' in sys.argv[1:]):
459
model_group.add_argument("--model", **model_kwargs["model"])
460
model_group.add_argument("--task", **model_kwargs["task"])
461
model_group.add_argument("--tokenizer", **model_kwargs["tokenizer"])