InvokeAI/invokeai/backend/util
Lincoln Stein 10d3bccf32
Mac MPS FP16 fixes (#3641)
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.
2023-07-07 17:43:23 -04:00
..
__init__.py add support for an autoimport models directory scanned at startup time 2023-06-25 18:50:15 -04:00
devices.py Mac MPS FP16 fixes (#3641) 2023-07-07 17:43:23 -04:00
log.py all vestiges of ldm.invoke removed 2023-03-03 01:02:00 -05:00
logging.py resolve conflicts 2023-06-10 10:13:54 -04:00
mps_fixes.py Update mps_fixes.py - additional torch op for nodes 2023-07-05 17:47:23 -04:00
util.py add support for an autoimport models directory scanned at startup time 2023-06-25 18:50:15 -04:00