服务端部署
								1
#54 opened 1 day ago
		by
		
				
 Alive2June
							
						Alive2June
	
 
							paddleocr-vl can inferenced by vllm?
								1
#53 opened 1 day ago
		by
		
				
 sibylxi
							
						sibylxi
	
how do convert table OTSL format to HTML format ?
									1
	#52 opened 1 day ago
		by
		
				
 CCWM
							
						CCWM
	
Can't launch the model via docker
#51 opened 2 days ago
		by
		
				
 xne0n
							
						xne0n
	
PP-DocLayoutV2 没有提供inference.json参数文件,导致ONNX转换失败
									2
	#50 opened 3 days ago
		by
		
				
 nicozck
							
						nicozck
	
Layout Order random
									5
	#48 opened 3 days ago
		by
		
				
 Chgayot
							
						Chgayot
	
Layout Analysis Inference
🤝
							
						1
				
									4
	#46 opened 5 days ago
		by
		
				
 saikanov
							
						saikanov
	
 
							Upload yQNWqSPsTxoEXzFZPEWAU.jpeg
#45 opened 5 days ago
		by
		
				
 Citrus-777
							
						Citrus-777
	
Not able to run via docker: nvidia-container-cli: initialization error: load library failed: libnvidia-ml.so.1:
									2
	#44 opened 6 days ago
		by
		
				
 khanfarhan10
							
						khanfarhan10
	
 
							PaddleOCR Official Website is Now Live! 🎉
🔥
							🚀
							
						4
				
									1
	#43 opened 7 days ago
		by
		
				
 
							 ChengCui
						ChengCui
	
 
							ms-swift has supported inference, deployment, and fine-tuning of the PaddleOCR-VL model.
🚀
							🔥
							
						7
				
									4
	#42 opened 8 days ago
		by
		
				
 hu5enpai
							
						hu5enpai
	
执行paddleocr install_genai_server_deps vllm失败
									1
	#41 opened 8 days ago
		by
		
				
 Hugger819
							
						Hugger819
	
Help to run PaddleOCR-VL model via Docker
								5
#39 opened 8 days ago
		by
		
				
 phamgialinhlx
							
						phamgialinhlx
	
Need PaddleOCR-VL for lower compute capability
									1
	#38 opened 9 days ago
		by
		
				
 adnanPBI
							
						adnanPBI
	
Need detailed guide to prepare dataset for fine-tuning
									1
	#37 opened 9 days ago
		by
		
				
 adnanPBI
							
						adnanPBI
	
docker run failed and how to fix it?
									2
	#36 opened 10 days ago
		by
		
				
 cbhcba
							
						cbhcba
	
Set use_doc_preprocessor, but the models for doc preprocessor are not initialized.
									6
	#35 opened 10 days ago
		by
		
				
 Sandstone0525
							
						Sandstone0525
	
运行的时候有warning: Setting `pad_token_id` to `eos_token_id`:2 for open-end generation.不影响运行,可以无视吗?
									1
	#34 opened 10 days ago
		by
		
				
 tarjintor
							
						tarjintor
	
Can't make it run on Colab
								1
#33 opened 10 days ago
		by
		
				
 sanggusti
							
						sanggusti
	
 
							whats up with all the recent OCR models being released
									1
	#30 opened 11 days ago
		by
		
				
 evewashere
							
						evewashere
	
benchmark with DeepSeek-OCR included
🤗
							🚀
							
						8
				
									1
	#29 opened 11 days ago
		by
		
				
 
							 jzhang533
						jzhang533
	
 
							A100显卡,如何使用SGLang或VLLM部署
									2
	#28 opened 11 days ago
		by
		
				
 Alive2June
							
						Alive2June
	
 
							Đã có ai cài được chưa, sao cài PaddleOCR khó vậy nhỉ, từ cài môi trương win, ubuntu đều lỗi
									1
	#27 opened 11 days ago
		by
		
				
 dongnchdg
							
						dongnchdg
	
The Kernel crashed, anyone can please help.
									10
	#24 opened 12 days ago
		by
		
				
 ahnulxy
							
						ahnulxy
	
 
							Genunie User Reviews and Questions on Repo PaddlePaddle/PaddleOCR-VL
#23 opened 12 days ago
		by
		
				
 DeepNLP
							
						DeepNLP
	
AssertionError: Variable dtype not match, Variable [ linear_164.w_0 ] need tensor with dtype paddle.float32 but load tensor with dtype paddle.bfloat16
➕
							
						6
				
									1
	#22 opened 12 days ago
		by
		
				
 renoyuan
							
						renoyuan
	
Docker not working on GH 200 with aarch64 cpu architecture
									1
	#19 opened 13 days ago
		by
		
				
 GodsonLight
							
						GodsonLight
	
没有找到显卡驱动
									5
	#18 opened 14 days ago
		by
		
				
 wuzhanliai21
							
						wuzhanliai21
	
 
							Request to add more hardware support
👍
							
						2
				
									2
	#17 opened 14 days ago
		by
		
				
 snnh
							
						snnh
	
How to convert charts to table?
									1
	#16 opened 14 days ago
		by
		
				
 NirajRajai
							
						NirajRajai
	
layoutmodel
									2
	#14 opened 14 days ago
		by
		
				
 prudant
							
						prudant
	
 
							any possibility to finetune the model ?
									2
	#13 opened 14 days ago
		by
		
				
 StephennFernandes
							
						StephennFernandes
	
 
							where exactly can i find the list of supported languages that this model supports ?
									2
	#12 opened 14 days ago
		by
		
				
 StephennFernandes
							
						StephennFernandes
	
 
							Unrecognized footer
									4
	#11 opened 14 days ago
		by
		
				
 Maguro97
							
						Maguro97
	
Enable download counts
									2
	#9 opened 14 days ago
		by
		
				
 merve
							
						merve
	
 
							模型在V100上报错
									6
	#6 opened 15 days ago
		by
		
				
 yijinsheng
							
						yijinsheng
	
无法直接通过调用openai compatible api的方式使用?
									3
	#5 opened 15 days ago
		by
		
				
 burrowswang
							
						burrowswang
	
PaddleOCR-VL Training example
									1
	#4 opened 15 days ago
		by
		
				
 imneonizer
							
						imneonizer
	
Only for image? not support PDF?
									1
	#3 opened 15 days ago
		by
		
				
 stephonye
							
						stephonye
	
GGUF or MLX support?
👍
							
						18
				
									5
	#2 opened 15 days ago
		by
		
				
 smcleod
							
						smcleod
	
 
							How to use transformers for PaddleOCR-VL inferencing?
➕
							
						8
				
									13
	#1 opened 15 days ago
		by
		
				
 stzhao
							
						stzhao
	
 
							