Jonathan 0d7205ff79 Handle mixed-dtype mismatches in autocast linear and conv wrappers (#9006) ...

* Handle CustomConv2d bias dtype mismatches

* Fix mixed-dtype autocast regressions

* Format custom_conv2d with ruff

2026-04-20 20:31:35 +00:00

..

configs

Feat[model support]: Qwen Image — full pipeline with edit, generate LoRA, GGUF, quantization, and UI (#9000)

2026-04-12 14:39:13 +02:00

data

Get convert_flux_kohya_state_dict_to_invoke_format(...) working, with unit tests.

2024-09-15 04:39:56 +03:00

load

Handle mixed-dtype mismatches in autocast linear and conv wrappers (#9006)

2026-04-20 20:31:35 +00:00

model_loading

Ruff formatting

2025-03-26 12:30:31 +11:00

model_metadata

Add unit test

2024-03-19 01:16:11 -04:00

util

refactor: model manager v3 (#8607)

2025-10-15 10:18:53 +11:00

model_manager_fixtures.py

refactor: model manager v3 (#8607)

2025-10-15 10:18:53 +11:00

test_external_api_config.py

External models (Gemini Nano Banana & OpenAI GPT Image) (#8633) (#8884)

2026-04-20 17:13:26 +00:00

test_libc_util.py

Tidy names and locations of modules

2024-03-01 10:42:33 +11:00

test_memory_snapshot.py

final tidying before marking PR as ready for review

2024-03-01 10:42:33 +11:00

test_model_load_optimization.py

Tidy names and locations of modules

2024-03-01 10:42:33 +11:00