-
Notifications
You must be signed in to change notification settings - Fork 1
Closed
Description
The app starts and loads models but generation fails with:
Generation Failed: MPS backend out of memory (MPS allocated: 27.06 GB, other allocations: 512.00 KB, max allowed: 27.20 GB). Tried to allocate 192.00 MB on private pool. Use PYTORCH_MPS_HIGH_WATERMARK_RATIO=0.0 to disable upper limit for memory allocations (may cause system failure).
Reactions are currently unavailable