master

GGitHubFix issue with bypass loras and fused paths. (#16862)

d91ed5f5创建于 2 天前历史提交

文件	最后提交记录	最后更新时间
__init__.py	[Weight-adapter/Trainer] Bypass forward mode in Weight adapter system (#11958) * Add API of bypass forward module * bypass implementation * add bypass fwd into nodes list/trainer	8 个月前
base.py	MPDynamic: force load flux img_in weight (Fixes flux1 canny+depth lora crash) (#12446) * lora: add weight shape calculations. This lets the loader know if a lora will change the shape of a weight so it can take appropriate action. * MPDynamic: force load flux img_in weight This weight is a bit special, in that the lora changes its geometry. This is rather unique, not handled by existing estimate and doesn't work for either offloading or dynamic_vram. Fix for dynamic_vram as a special case. Ideally we can fully precalculate these lora geometry changes at load time, but just get these models working first.	7 个月前
boft.py	[Weight-adapter/Trainer] Bypass forward mode in Weight adapter system (#11958) * Add API of bypass forward module * bypass implementation * add bypass fwd into nodes list/trainer	8 个月前
bypass.py	Fix issue with bypass loras and fused paths. (#16862)	2 天前
glora.py	[Weight-adapter/Trainer] Bypass forward mode in Weight adapter system (#11958) * Add API of bypass forward module * bypass implementation * add bypass fwd into nodes list/trainer	8 个月前
loha.py	[Weight-adapter/Trainer] Bypass forward mode in Weight adapter system (#11958) * Add API of bypass forward module * bypass implementation * add bypass fwd into nodes list/trainer	8 个月前
lokr.py	[Weight-adapter/Trainer] Bypass forward mode in Weight adapter system (#11958) * Add API of bypass forward module * bypass implementation * add bypass fwd into nodes list/trainer	8 个月前
lora.py	MPDynamic: force load flux img_in weight (Fixes flux1 canny+depth lora crash) (#12446) * lora: add weight shape calculations. This lets the loader know if a lora will change the shape of a weight so it can take appropriate action. * MPDynamic: force load flux img_in weight This weight is a bit special, in that the lora changes its geometry. This is rather unique, not handled by existing estimate and doesn't work for either offloading or dynamic_vram. Fix for dynamic_vram as a special case. Ideally we can fully precalculate these lora geometry changes at load time, but just get these models working first.	7 个月前
oft.py	[Weight-adapter/Trainer] Bypass forward mode in Weight adapter system (#11958) * Add API of bypass forward module * bypass implementation * add bypass fwd into nodes list/trainer	8 个月前