fix: never auto-select MPS device for text watermark detection (#99)

Browse Source

resolve_device() auto-selects 'mps' whenever torch reports it available.
Both schemes this harness can load build a device-bound RNG in their
constructor:

  KGW.__init__      -> torch.Generator(device=config.device)   (kgw.py)
  SynthID.__init__  -> torch.Generator(device=config.device)   (synthid.py)

torch.Generator supports only the 'cpu' and 'cuda' device types, so on
Apple Silicon a resolved 'mps' device raises

  RuntimeError: Device type MPS is not supported for torch.Generator() api

and both the `detect` and `watermark` subcommands crash out of the box on
any Mac where torch reports MPS available.

Drop the mps branch from the auto path so `--device auto` resolves to cpu
on CUDA-less machines. `--device mps` is still honored as an explicit
override (resolve_device returns any non-'auto' value unchanged), so this
changes only the automatic default, not the ability to opt in.

Co-authored-by: Guillaume Meyer (The Opinionated Man) <1385518+guillaumemeyer@users.noreply.github.com>

...

This commit is contained in:

rsbarua

2026-08-16 18:19:59 -07:00

committed by GitHub

co-authored by Guillaume Meyer

parent 27c1ce864e

commit e3eb602128

Show all changes Ignore whitespace when comparing lines Ignore changes in amount of whitespace Ignore changes in whitespace at EOL

Download Patch File Download Diff File Expand all files Collapse all files

Diff Content Not Available