Files
facefusion/tests
7990faa38c Revamp execution provider overrides/adjustments (#1206)
* Split provider hooks into override/adjust with cached CoreML base

Replace the single resolve_inference_providers processor hook with two:
override_inference_providers (full replacement) and adjust_inference_providers
(merge options onto the base providers built by create_inference_providers).
This lets CoreML processors inherit ModelCacheDirectory + SpecializationStrategy
from the base while layering ModelFormat/MLComputeUnits on top.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01HTQCZiYjJyUX11bDpbRSiB

* fix caching for execution provider by having override and adjust ways

* fix caching for execution provider by having override and adjust ways

* fix lint

* use proper pytest fixtures

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-07-27 12:16:33 +02:00
..
2023-08-21 16:19:01 +02:00
2025-04-28 10:03:25 +02:00
2026-06-30 15:00:02 +02:00
2026-06-30 15:00:02 +02:00
2026-04-19 21:17:39 +02:00
2024-12-24 12:46:56 +01:00
2026-03-08 11:00:45 +01:00
2026-07-25 11:47:36 +02:00
2026-07-23 18:06:40 +02:00
2025-04-28 10:03:24 +02:00
2025-09-08 10:43:58 +02:00
2024-09-20 17:27:50 +02:00
2026-03-08 11:00:45 +01:00
2025-11-03 14:05:15 +01:00
2024-09-20 17:27:50 +02:00
2025-12-13 08:37:15 +01:00
2025-06-17 10:47:02 +02:00
2026-06-30 15:00:02 +02:00
2025-09-08 10:43:58 +02:00
2026-07-26 10:08:47 +02:00