Tim Z. Xiao comments

Results 7 comments of


                                            Tim Z. Xiao

Question: out of memory when generating translate_enzh_wmt32k data set

Hello all, any updates on this? I also encountered the massive use of memory when try to run t2t-datagen for translate_enzh_wmt32k

pretrained model

The website is up now. Here is the link to the [pretrained model](https://drive.google.com/drive/folders/1DQuXEiN-XgftyfFC4Vu7ugMoVhgRzSng?usp=sharing). To use the pretrained model, you can refer to the [backend of the website](https://github.com/timxzz/Facial_Expression_Modifier_Backend). Let me know...

pretrained model

@sayeh1994 If you have the datasets, you will need to first preprocess it into 128x128. The preprocessing code is in https://github.com/timxzz/GANs/blob/master/Face/Face_data/Image_preprocessing.ipynb

don't see the main or run .py

@MNCTTY Yes, it should be like this as it is a API backend, it doesn't have website to get to. However, with the pretrained model, you should be able to...

[Usage]: How to determine whether the vllm engine is full with requests or not

@robertgshaw2-neuralmagic I am not sure why the OP wants this info, but for me, I would like to know if the engine is at its capacity, so I can decide...

[Usage]: How to determine whether the vllm engine is full with requests or not

Thanks for the timely reply! Is there a limit on how many request it can handle or queue? Or it will start rejecting when the limit is reached and the...

[Usage]: How to determine whether the vllm engine is full with requests or not

I found #2492 and #3561 are also useful for answering this question.