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 2025-02-12 18:57:01 -08:00
commit 083ee86d89
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

@ -449,6 +449,7 @@ def LlamaAttention_fast_forward(
else:
# Grouped query attention
if SDPA_HAS_GQA:
print("=====================")
# Needs (batch_size, n_heads, seq_len, head_dim)
# is_casual and attention_mask must not be both set!
A = scaled_dot_product_attention(Q, K, V, attn_mask = attention_mask, is_causal = False, enable_gqa = n_groups != 1)