5 commits

Author	SHA1	Message	Date
PanQiWei	9155ef3038	fix using wrong attribute	2023-08-06 15:37:11 +08:00
PanQiWei	ab6faa6496	implement gptj attention and mlp fused ops injection logic	2023-08-06 14:55:06 +08:00
PanQiWei	d5429441ef	add GPTJ fused attention module	2023-05-14 16:17:21 +08:00
PanQiWei	a2abff983e	support dispatch layers to different devices when loading pretrained model before quantization	2023-04-27 02:24:08 +08:00
PanQiWei	229b61e20e	first init	2023-04-14 01:09:40 +08:00