doctorpangloss 83184916c1 Improvements to GGUF ... - GGUF now works and included 4 bit quants, this will allow WAN to run on 24GB VRAM GPUs - logger only shows full stack for errors - helper functions for colab notebook - fix nvcr.io auth error - lora issues are now reported better - model downloader will use huggingface cache and symlinking if it is supported on your platform - torch compile node now correctly patches the model before compilation		2025-07-30 18:28:52 -07:00
..
chainner_models	Improving MLLM/VLLM support and fixing bugs	2025-02-05 14:02:28 -08:00
constants	update upstream for flux fixes	2025-07-09 06:28:17 -07:00
controlnet_aux	Improving MLLM/VLLM support and fixing bugs	2025-02-05 14:02:28 -08:00
language_web	Move language extensions in order to support packagized frontend	2025-03-05 10:39:31 -08:00
nodes	Improvements to GGUF	2025-07-30 18:28:52 -07:00
paligemma	Improving MLLM/VLLM support and fixing bugs	2025-02-05 14:02:28 -08:00
__init__.py	move this back since the issue is resolved	2023-08-22 18:00:18 -07:00