mirror of
https://github.com/invoke-ai/InvokeAI
synced 2026-04-25 16:22:09 +02:00
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. |
||
|---|---|---|
| .. | ||
| __init__.py | ||
| devices.py | ||
| log.py | ||
| logging.py | ||
| mps_fixes.py | ||
| util.py | ||