Closed RissyRan closed 1 month ago
Thank you @RissyRan for adding dropping strategy!! I just added some nit.
Thank you @RissyRan for adding dropping strategy!! I just added some nit.
Thanks Zhiyu! Have you published comments?
Thank you @RissyRan for adding dropping strategy!! I just added some nit.
Thanks Zhiyu! Have you published comments?
Just published.
Description
Enable token dropping for matmul implementation
Next steps:
Test
Have a unite test to check a single layer output (become dropless if capacity factor is large enough):