-
Notifications
You must be signed in to change notification settings - Fork 5.8k
standardize moe permute unpermute #73365
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
standardize moe permute unpermute #73365
Conversation
/re-run all-failed |
1 similar comment
/re-run all-failed |
/re-run all-failed |
/re-run all-failed |
hidden_states: Tensor, | ||
scale: Tensor | None, | ||
expert_routemap_topk: Tensor, | ||
expert_prob_topk: Tensor, | ||
topk: int, | ||
num_experts: int, | ||
tokens_per_expert: list, | ||
padding_multiplex: int, | ||
padding_alignment: int, | ||
name: str | None = None, | ||
): | ||
) -> tuple[Tensor, Tensor, Tensor, Tensor]: | ||
if in_dynamic_or_pir_mode(): |
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.
加API注释
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.
两个python文件是不可以合并?
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.
/re-run all-failed |
/re-run all-failed |
PR Category
User Experience
PR Types
Bug fixes
Description
standardize moe_unpermute and moe_permute api interface and unit test