Beatlesso comments

Repositories
Issues
Comments

Results 2 comments of


                                            Beatlesso

Do tensorrt 9.2 support flash attention v2

I built the following module with FlashAttention and saved it as a pth model: ``` import torch import torch.nn as nn import torch.nn.functional as F from flash_attn import flash_attn_func class...

Start training but only output config information

> Seems that you are having a hanging issue. Could you refer to [this issue](https://github.com/princeton-nlp/LLM-Shearing/issues/53) and see if the solution helps? Thanks, that solved my problem. One more question for...