Update llama.py

This commit is contained in:
Daniel Han 2025-03-21 15:27:47 -07:00
commit fa910abecf

View file

@ -1016,6 +1016,7 @@ def CausalLM_fast_forward(fast_forward_inference):
logits_to_keep: Optional[int] = 0,
*args, **kwargs,
) -> Union[Tuple, CausalLMOutputWithPast]:
print(past_key_values)
if past_key_values is not None:
outputs = fast_forward_inference(
self,