Ethanfel cde280049b fix: correct LoRALinear dtype and remove unused import ...

- LoRALinear now creates lora_A/lora_B with dtype matching the base
  linear's weight, preventing a float32/bf16 mismatch at forward time
  when the generator is loaded in bf16 or fp16.
- Remove unused `import math` from train_lora.py.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

2026-04-05 14:57:09 +02:00

..

data

chore: vendor selva_core from jnwnlee/selva@d7d40a9

2026-04-04 15:18:09 +02:00

ext

fix: BigVGANv2._from_pretrained() compat with newer huggingface_hub

2026-04-04 16:51:48 +02:00

model

fix: correct LoRALinear dtype and remove unused import

2026-04-05 14:57:09 +02:00

utils

chore: vendor selva_core from jnwnlee/selva@d7d40a9

2026-04-04 15:18:09 +02:00

__init__.py

chore: vendor selva_core from jnwnlee/selva@d7d40a9

2026-04-04 15:18:09 +02:00