Consolidate metal & cuda backend in AOT and runtime #15424
Description
🚀 The feature, motivation and pitch
Removing duplicate code, AOT has a lot of work to do, runtime is in a better shape.
Also, let's use SlimTensor!
Alternatives
No response
Additional context
No response
RFC (Optional)
No response
Metadata
Metadata
Assignees
Labels
No labels
Type
Projects
Status