Skip to content

Fix group offloading for quanto-quantized models and the use_stream path for quantized tensor subclasses#14038

Open
Sunt-ing wants to merge 1 commit into
huggingface:mainfrom
Sunt-ing:0
Open

Fix group offloading for quanto-quantized models and the use_stream path for quantized tensor subclasses#14038
Sunt-ing wants to merge 1 commit into
huggingface:mainfrom
Sunt-ing:0