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, 23:30 UTC
[Misc] Fix typo in the example file (#12896)
Signed-off-by: Zhao Ke <yingxiongraomingzk@gmail.com>
Ke Zhao committed
Feb 8, 2025 at 14:56 UTC
cc01223f3ba0434487a0179a2ccd2107bf3c93cb
1 file changed
+3
-3
examples/online_serving/openai_chat_embedding_client_for_multimodal.py
+3
-3
@@ -44,7 +44,7 @@ def vlm2vec():
44
45
def dse_qwen2_vl(inp: dict):
46
# Embedding an Image
47
- if inp["dtype"] == "image":
47
+ if inp["type"] == "image":
48
messages = [{
49
"role":
50
"user",
@@ -113,10 +113,10 @@ if __name__ == '__main__':
113
vlm2vec()
114
elif args.model == "dse_qwen2_vl":
115
dse_qwen2_vl({
116
- "dtye": "image",
116
+ "type": "image",
117
"image_url": image_url,
118
})
119
dse_qwen2_vl({
120
- "dtype": "text",
120
+ "type": "text",
121
"content": "What is the weather like today?",
122
})