aboutsummaryrefslogtreecommitdiffstats
path: root/modules/mac_specific.py
AgeCommit message (Collapse)AuthorLines
2023-08-13Remove duplicate code for torchsde randnbrkirch-3/+0
2023-08-09split shared.py into multiple files; should resolve all circular reference ↵AUTOMATIC1111-2/+2
import errors related to shared.py
2023-07-12Don't do MPS GC when there's a latent that could still be sampledAarni Koskela-0/+4
2023-07-12Add correct logger nameAarni Koskela-1/+1
2023-07-11Fix MPS cache cleanupAarni Koskela-0/+14
Importing torch does not import torch.mps so the call failed.
2023-07-06Fix warning of 'has_mps' is deprecated from PyTorchHao-Wu-9/+14
2023-05-11Autofix Ruff W (not W605) (mostly whitespace)Aarni Koskela-2/+2
2023-05-10imports cleanup for ruffAUTOMATIC-1/+0
2023-05-09Fix generation with k-diffusion/UniPC on x64 Macsbrkirch-0/+5
2023-05-09Remove PyTorch 2.0 checkbrkirch-2/+2
Apparently the commit in the main branch of pytorch/pytorch that fixes this issue didn't make it into PyTorch 2.0.1, and since it is unclear exactly which release will have it we'll just always apply the workaround so a crash doesn't occur regardless.
2023-03-24Add workaround for MPS layer_norm on PyTorch 2.0brkirch-1/+3
On PyTorch 2.0, with MPS layer_norm only accepts float32 inputs. This was fixed shortly after 2.0 was finalized so the workaround can be applied with an exact version match.
2023-03-24Add workaround for broken nn.Linear on macOS 13.2brkirch-0/+5
Credit to danieldk (https://github.com/explosion/curated-transformers/pull/124) for the workaround this is based on.
2023-03-11Remove test, use bool tensor fix by defaultbrkirch-2/+1
The test isn't working correctly on macOS 13.3 and the bool tensor fix for cumsum is currently always needed anyway, so enable the fix by default.
2023-02-04Remove unused codebrkirch-3/+0
2023-02-01Refactor Mac specific code to a separate filebrkirch-0/+56
Move most Mac related code to a separate file, don't even load it unless web UI is run under macOS.