ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update llama.py

Browse source
This commit is contained in:
Daniel Han 2025-03-21 16:53:44 -07:00
commit 2b91bc983d
1 changed files with 1 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

1
unsloth/models/llama.py
View file

@ -422,6 +422,7 @@ def LlamaAttention_fast_forward(
V = torch.cat([past_key_value[1], V], dim = 2)
pass
past_key_value = (K, V) if use_cache else None
print(bsz, q_len, past_key_value[0].shape, past_key_value[1].shape)
# Attention module
if (not HAS_FLASH_ATTENTION and HAS_XFORMERS and attention_mask is None):