Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

small improvement #12359

Merged
merged 1 commit into from
Nov 7, 2024
Merged

small improvement #12359

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 2 additions & 6 deletions python/llm/src/ipex_llm/transformers/models/qwen2.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -167,12 +167,8 @@ def qwen2_model_forward(
from transformers.models.qwen2.modeling_qwen2 import _prepare_4d_causal_attention_mask_for_sdpa
from transformers.models.qwen2.modeling_qwen2 import _prepare_4d_causal_attention_mask

# ipex-llm changes start: don't generate `attention_mask` in specific cases
if seq_length == 1 or batch_size == 1 and use_sdp_causal(
seq_length, seq_length + past_key_values_length,
self.config.hidden_size // self.config.num_attention_heads,
inputs_embeds, self.training
):
# ipex-llm changes start: don't generate `attention_mask` in decode phase
if seq_length == 1:
attention_mask = None
# ipex-llm changes end
elif self._attn_implementation == "flash_attention_2":
Expand Down
Loading