ShreejithSG c54e0737d0 Address PR comments: GLM-Image Port to FastVideo- Replaced diffusers FeedForward with FastVideo MLP in DiT.- Moved SDPAMetadata import to top of attention layer for cleaner code.- Removed unnecessary __call__ override from pipeline to use standard composition.- Consolidated CFG into a single batched pass with concatenated embeddings for performance.- Fixed attention mask compatibility issues with optimized FLASH_ATTN backend.- Robustly patched flash_attn unpad utility for variable version return values.

2026-07-07 15:00:48 -07:00

..

benchmarks

[feat] Optimize distributed weight loading in multi-node training (#572)

2026-05-21 16:59:48 +00:00

__init__.py

[Feature] Remove V1 folder (#642)

2025-07-24 22:43:12 -07:00

component_loader.py

Address PR comments: GLM-Image Port to FastVideo- Replaced diffusers FeedForward with FastVideo MLP in DiT.- Moved SDPAMetadata import to top of attention layer for cleaner code.- Removed unnecessary __call__ override from pipeline to use standard composition.- Consolidated CFG into a single batched pass with concatenated embeddings for performance.- Fixed attention mask compatibility issues with optimized FLASH_ATTN backend.- Robustly patched flash_attn unpad utility for variable version return values.

2026-07-07 15:00:48 -07:00

fsdp_load.py

[bugfix] fixing denoising time in the fastwan script (#1480)

2026-06-23 10:01:23 -07:00

utils.py

[Feature] Remove V1 folder (#642)

2025-07-24 22:43:12 -07:00

weight_utils.py

[feat] Optimize distributed weight loading in multi-node training (#572)

2026-05-21 16:59:48 +00:00