lum3on 0b0753e708 Fix VAE SageAttention integration tensor shape mismatch ...

- Add proper tensor reshaping in vae_sage_attention() wrapper
- Convert VAE format (B, C, H, W) to SageAttention format (B, seq_len, dim)
- Add fallback mechanism to pytorch attention if SageAttention fails
- Enable SageAttention selection in vae_attention() function
- Fixes ValueError: too many values to unpack (expected 3) error
- Maintains compatibility with existing VAE attention functions

This resolves the tensor shape incompatibility between VAE spatial attention
and SageAttention sequence attention, allowing VAE operations to benefit from
SageAttention optimization when --use-sage-attention flag is enabled.

2025-09-16 00:58:48 +02:00

..

__init__.py

Initial commit.

2023-01-16 22:37:14 -05:00

mmdit.py

Enable Runtime Selection of Attention Functions (#9639)

2025-09-12 18:07:38 -04:00

model.py

Fix VAE SageAttention integration tensor shape mismatch

2025-09-16 00:58:48 +02:00

openaimodel.py

Lint unused import (#5973)

2024-12-09 15:24:39 -05:00

upscaling.py

Lint unused import (#5973)

2024-12-09 15:24:39 -05:00

util.py

Replace print with logging (#6138)

2024-12-20 16:24:55 -05:00