-
Notifications
You must be signed in to change notification settings - Fork 2.1k
Add Qwen3-Moe fuse qkv/ffn modeling #2981
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.
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
base: develop
Are you sure you want to change the base?
Conversation
|
Thanks for your contribution! |
Codecov Report❌ Patch coverage is ❌ Your patch status has failed because the patch coverage (35.90%) is below the target coverage (80.00%). You can increase the patch coverage or adjust the target coverage. Additional details and impacted files@@ Coverage Diff @@
## develop #2981 +/- ##
==========================================
Coverage ? 31.35%
==========================================
Files ? 420
Lines ? 68728
Branches ? 0
==========================================
Hits ? 21547
Misses ? 47181
Partials ? 0 ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
| max_sequence_length = self.config.max_sequence_length | ||
| bsz = hidden_states.shape[0] * self.config.tensor_parallel_degree // max_sequence_length | ||
| q_len = max_sequence_length | ||
| if not self.fuse_attention_qkv: |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
补充一个fuse 和非fuse的单测 logits对比单测 ,类似下面这种https://github.com/PaddlePaddle/PaddleFormers/blob/develop/tests/transformers/qwen3moe/test_modeling.py#L396
No description provided.