support transformers 4.34+ for llama (#9229)
This commit is contained in:
parent
7e96d3e79a
commit
118249b011
1 changed files with 2 additions and 0 deletions
|
|
@ -79,6 +79,8 @@ def llama_attention_forward_4_31(
|
|||
past_key_value: Optional[Tuple[torch.Tensor]] = None,
|
||||
output_attentions: bool = False,
|
||||
use_cache: bool = False,
|
||||
padding_mask: Optional[torch.LongTensor] = None,
|
||||
**kwargs,
|
||||
) -> Tuple[torch.Tensor, Optional[torch.Tensor], Optional[Tuple[torch.Tensor]]]:
|
||||
bsz, q_len, _ = hidden_states.size()
|
||||
device = hidden_states.device
|
||||
|
|
|
|||
Loading…
Reference in a new issue