lunar

Hi, cause I wanted to apply it in chinese, so i didn't ues your embedings. I found that the loglike is normal where the corpus contains only one doc. [Here](https://1drv.ms/u/s!Ao-mp6ZKSHNwti2N6yATuTVy4Y8R)...

> Thank you. Basically I just run your demo [colab notebook](https://colab.research.google.com/drive/1Q4eNhhhLcgOP4hHqwZwU1ijOlabgve1W?usp=sharing#scrollTo=zlDr95m6weQz) for the image captioning. The torch version is 1.12.0+cu113. I ran all cells and in the end I just...

> @narendasan I did that, I can see that the linear was getting None on the bias parameter and yet torch-tensorrt did the transformation as if it is a regular...

> > > @narendasan I did that, I can see that the linear was getting None on the bias parameter and yet torch-tensorrt did the transformation as if it is...

More information: I test TensorRT in an Encoder Layer module, basically, it is an Attention module above with some fc (full-connected) layers, layer norm and dropout layers. The results show...

> I'm getting this output performance using your script: > > ``` > Original Model 3.2848336696624756 > Jit Script Model 2.7592527866363525 > Jit Script Model after optimization 2.0758402347564697 > TensorRT...

> Thanks for reporting :) Should be fixed in #438 Hello, has it been fixed right now?

Thank you. I have tried the newest commit of `xformers`, and the `RuntimeError: unsupported output type: int, from operator: xformers::efficient_attention_forward_generic` is solved. However, another problem appears. When I run the...

然而猎人更惨。。 

I meet the same problem when I try to use AutoGPTQ to quantize my model. Is there any solution to solve it now?