Max Buckley 4d04e830bc Fix CUDA-graph replay race + many_faces enhancer regression ...

Two issues surfaced in post-squash review of f65aeae:

1. CUDA-graph replay buffers were shared across threads with no lock.
   `_cuda_graph_swap_inference` mutates module-level ort_input/ort_latent
   and runs run_with_iobinding — concurrent swap calls on Windows/CUDA
   could overwrite each other's bound input buffers before replay,
   producing wrong-face output. Added `_cuda_graph_lock` around the
   full update/run/read sequence.

2. Face enhancer loop unconditionally broke after the first face, so
   `many_faces=True` silently enhanced only one face. Also, the
   single-slot temporal cache would paste the same enhancement onto
   every target if reused in many-faces mode. Gated the break on
   `not many_faces_mode` and disabled the cache path in that mode.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

2026-04-22 11:08:23 +02:00

..

frame

Fix CUDA-graph replay race + many_faces enhancer regression

2026-04-22 11:08:23 +02:00

__init__.py

initial commit

2023-09-24 21:36:57 +08:00