It seems like register_offload_parameter is trying to offload the parameter to CPU or some non-gpu device, but maybe isn’t actually working. Maybe the offloading framework isn’t set up properly, a condition isn’t met, or the dict it’s offloading to is actually still in GPU memory. Either way, let's try the simple thing of not making the parameter and explicitly deleting weight_data.
В Совфеде ответили на слова Макрона об увеличении ядерных боеголовок у ФранцииКосачев заявил, что Франция в открытую увеличивает свой ядерный потенциал，推荐阅读51吃瓜获取更多信息
。关于这个话题，谷歌提供了深入分析
Share on X (Opens in new window)
Burns, the education consultant, said AI was, in some ways, a natural extension of the argument tech companies have made about the need for computers in school, which is that students are able to learn at their own pace, or seek out information of interest to them to initiate their own learning.。关于这个话题，超级权重提供了深入分析
Bibliographic Tools