Have example of GatedDeltaNet exporting #16708
Description
🚀 The feature, motivation and pitch
GatedDeltaNets are a compelling model architecture used in the NVidia jet nemotron models. Show case this to build an understanding of any gaps in export as well as performance (cuda needs a custom op)
Alternatives
No response
Additional context
No response
RFC (Optional)
No response
Metadata
Metadata
Assignees
Labels
No labels
Type
Projects
Status