rattus e136b6dbb0 dequantization offload accounting (fixes Flux2 OOMs - incl TEs) (#11171) ... * make setattr safe for non existent attributes Handle the case where the attribute doesnt exist by returning a static sentinel (distinct from None). If the sentinel is passed in as the set value, del the attr. * Account for dequantization and type-casts in offload costs When measuring the cost of offload, identify weights that need a type change or dequantization and add the size of the conversion result to the offload cost. This is mutually exclusive with lowvram patches which already has a large conservative estimate and wont overlap the dequant cost so\ dont double count. * Set the compute type on CLIP MPs So that the loader can know the size of weights for dequant accounting.		2025-12-08 23:21:31 -05:00
..
audio_encoders	…
cldm	Add better error message for common error. (#10846)	2025-11-23 04:55:22 -05:00
comfy_types	…
extra_samplers	…
image_encoders	…
k_diffusion	…
ldm	Properly load the newbie diffusion model. (#11172)	2025-12-07 07:44:55 -05:00
sd1_tokenizer	…
t2i_adapter	…
taesd	Support video tiny VAEs (#10884)	2025-11-28 19:40:19 -05:00
text_encoders	Fix qwen scaled fp8 not working with kandinsky. Make basic t2i wf work. (#11162)	2025-12-06 17:50:10 -08:00
weight_adapter	Fix loras not working on mixed fp8. (#10899)	2025-11-26 00:07:58 -05:00
checkpoint_pickle.py	…
cli_args.py	feat: Support ComfyUI-Manager for pip version (#7555)	2025-12-01 22:32:52 -05:00
clip_config_bigg.json	…
clip_model.py	…
clip_vision.py	…
clip_vision_config_g.json	…
clip_vision_config_h.json	…
clip_vision_config_vitl.json	…
clip_vision_config_vitl_336.json	…
clip_vision_config_vitl_336_llava.json	…
clip_vision_siglip_384.json	…
clip_vision_siglip_512.json	…
conds.py	…
context_windows.py	Context windows fixes and features (#10975)	2025-12-05 12:42:46 -08:00
controlnet.py	Fix Race condition in --async-offload that can cause corruption (#10501)	2025-10-29 17:17:46 -04:00
diffusers_convert.py	…
diffusers_load.py	…
float.py	…
gligen.py	…
hooks.py	…
latent_formats.py	Support video tiny VAEs (#10884)	2025-11-28 19:40:19 -05:00
lora.py	Support "transformer." LoRA prefix for Z-Image (#11135)	2025-12-08 15:17:26 -05:00
lora_convert.py	…
model_base.py	Properly load the newbie diffusion model. (#11172)	2025-12-07 07:44:55 -05:00
model_detection.py	Properly load the newbie diffusion model. (#11172)	2025-12-07 07:44:55 -05:00
model_management.py	Speed up lora compute and lower memory usage by doing it in fp16. (#11161)	2025-12-06 18:36:20 -05:00
model_patcher.py	dequantization offload accounting (fixes Flux2 OOMs - incl TEs) (#11171)	2025-12-08 23:21:31 -05:00
model_sampling.py	Refactor model sampling sigmas code. (#10250)	2025-10-08 17:49:02 -04:00
nested_tensor.py	WIP way to support multi multi dimensional latents. (#10456)	2025-10-23 21:21:14 -04:00
ops.py	Fix regression when text encoder loaded directly on GPU. (#11129)	2025-12-05 15:33:16 -05:00
options.py	…
patcher_extension.py	Fix order of inputs nested merge_nested_dicts (#10362)	2025-10-15 16:47:26 -07:00
pixel_space_convert.py	…
quant_ops.py	Make old scaled fp8 format use the new mixed quant ops system. (#11000)	2025-12-05 14:35:42 -05:00
rmsnorm.py	…
sample.py	Fix mistake. (#10484)	2025-10-25 23:07:29 -04:00
sampler_helpers.py	…
samplers.py	WIP way to support multi multi dimensional latents. (#10456)	2025-10-23 21:21:14 -04:00
sd.py	dequantization offload accounting (fixes Flux2 OOMs - incl TEs) (#11171)	2025-12-08 23:21:31 -05:00
sd1_clip.py	Make old scaled fp8 format use the new mixed quant ops system. (#11000)	2025-12-05 14:35:42 -05:00
sd1_clip_config.json	…
sdxl_clip.py	…
supported_models.py	Fix regression. (#11137)	2025-12-05 23:01:19 -05:00
supported_models_base.py	Fix some custom nodes. (#11134)	2025-12-05 18:25:31 -05:00
utils.py	dequantization offload accounting (fixes Flux2 OOMs - incl TEs) (#11171)	2025-12-08 23:21:31 -05:00