lunar

❓ [Question] Why TensorRT model is slower?

4

## ❓ Question Why TensorRT model is slower? I have tried TensorRT in a MHA (multihead attention) model, but found it is even slower than the jit scripted model. ##...

Problem about input embeddings generated by other algo.

5

Hi, I noticed that in your paper 6.1, as the inefficiency of optimizing likelihood function including both **Z** and **V**, you choose to divide the process into two stages. First,...

Re-pull request of https://github.com/PanQiWei/AutoGPTQ/pull/139 to avoid conflicts.

Something wrong with Markdown

1

Thanks for your notes first~ Something wrong with the grammar of markdown so the code in this formula cannot display correctly.