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, 19:30 UTC
[Bugfix] Fix VLM example typo (#6859)
Roger Wang committed
Jul 26, 2024 at 23:24 UTC
925de97e05dd4709fcd80691cb37da5e582c22e8
1 file changed
-1
examples/offline_inference_vision_language.py
-1
@@ -158,7 +158,6 @@ if __name__ == "__main__":
158
parser = FlexibleArgumentParser(
159
description='Demo on using vLLM for offline inference with '
160
'vision language models')
161
- args = parser.parse_args()
161
parser.add_argument('--model-type',
162
'-m',
163
type=str,