Update demo vllm script and docs
This commit is contained in:
+1
-1
@@ -4,7 +4,7 @@ gradio_image_annotation
|
||||
PyMuPDF
|
||||
openai
|
||||
qwen_vl_utils
|
||||
transformers==4.51.3
|
||||
transformers==4.56.1
|
||||
huggingface_hub
|
||||
modelscope
|
||||
# flash-attn==2.8.0.post2 # to speed up inference need flash-attn
|
||||
|
||||
Reference in New Issue
Block a user