You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
To support multiple allocator contexts in the tensor destructor, model interface should push and pop current allocator pointers to a queue in the default current context else risks failed destruction
The text was updated successfully, but these errors were encountered:
As a side note, the main issue is that we need to switch the ram & meta allocator back to those in the user space after model eval.
Since model eval will temporary switch allocators to the ones inside the model, not the ones in user space.
If we forget to switch allocators back, tensor deconstructor will fail.
To support multiple allocator contexts in the tensor destructor, model interface should push and pop current allocator pointers to a queue in the default current context else risks failed destruction
The text was updated successfully, but these errors were encountered: