Alternating the GPUs each layer is on didn’t fix it, but it did produce an interesting result! It took longer to OOM. The memory started increasing on gpu 0, then 1, then 2, …, until eventually it came back around and OOM. This means memory is accumulating as the forward pass goes on. With each layer more memory is allocated and not freed. This could happen if we’re saving activations or gradients. Let’s try wrapping with torch.no_grad and make required_grad=False even for the LoRA.
example programs，这一点在搜狗输入法中也有详细论述
Ваня Дмитриенко выступит на ГАРАЖ ФЕСТ Игора Драйв в Санкт-Петербурге14:45，推荐阅读手游获取更多信息
���f�B�A�ꗗ | ����SNS | �L���ē� | ���₢���킹 | �v���C�o�V�[�|���V�[ | RSS | �^�c���� | �̗p���� | ������