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, 21:00 UTC
[Misc] fixed 'required' is an invalid argument for positionals (#13948)
Signed-off-by: chaunceyjiang <chaunceyjiang@gmail.com>
Chauncey committed
Feb 27, 2025 at 17:06 UTC
10c3b8c1cf3b803db5d302a61c19c2aecdddf041
1 file changed
+1
-1
examples/online_serving/openai_chat_embedding_client_for_multimodal.py
+1
-1
@@ -102,7 +102,7 @@ if __name__ == '__main__':
102
parser = argparse.ArgumentParser(
103
"Script to call a specified VLM through the API. Make sure to serve "
104
"the model with --task embed before running this.")
105
- parser.add_argument("model",
105
+ parser.add_argument("--model",
106
type=str,
107
choices=["vlm2vec", "dse_qwen2_vl"],
108
required=True,