Mirrored_Repos/InvokeAI
1
0
Fork 0
mirror of https://github.com/invoke-ai/InvokeAI synced 2024-08-30 20:32:17 +00:00
Code Issues Packages Projects Releases Wiki Activity

Mac MPS FP16 fixes (#3641)

Browse Source 
This PR is to allow FP16 precision to work on Macs with MPS. In
addition, it centralizes the torch fixes/workarounds required for MPS
into a new backend utility `mps_fixes.py`. This is conditionally
imported in `api_app.py`/`cli_app.py`.

Many MANY thanks to @StAlKeR7779 for patiently working to debug and fix
these issues.
This commit is contained in:
Lincoln Stein
2023-07-07 17:43:23 -04:00
committed by GitHub
parent fefe56599f f610045a14
commit 10d3bccf32
9 changed files with 113 additions and 73 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
invokeai/backend/util/devices.py
View File

@ -29,6 +29,8 @@ def choose_precision(device: torch.device) -> str:
device_name = torch.cuda.get_device_name(device)
if not ("GeForce GTX 1660" in device_name or "GeForce GTX 1650" in device_name):
return "float16"
elif device.type == "mps":
return "float16"
return "float32"