Rattus f7aebddcf6 model_management: lazy-cache aimdo_tensor ...

These tensors cosntructed from aimdo-allocations are CPU expensive to
make on the pytorch side. Add a cache version that will be valid with
signature match to fast path past whatever torch is doing.

2026-02-11 23:26:04 +10:00

41 KiB

Raw Blame History

View Raw