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-Chen 2024-02-01 23:41:32 +11:00
commit abc47836dc
1 changed files with 2 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

4
unsloth/models/llama.py
View file

@ -268,8 +268,8 @@ def LlamaAttention_fast_forward_inference(
self.paged_attention_K[:,:,:kv_seq_len,:] = K1
self.paged_attention_V[:,:,:kv_seq_len,:] = V1
pass
Kn = self.paged_attention_K[:,:,seq_len,:] = K1
Vn = self.paged_attention_V[:,:,seq_len,:] = V1
Kn = self.paged_attention_K[:,:,seq_len,:] = Kn
Vn = self.paged_attention_V[:,:,seq_len,:] = Vn
# Grouped query attention
if n_groups != 1: