我32G的显存都不够，一直爆显存，什么设置也没有动，不知道什么问题。
torch.OutOfMemoryError: CUDA out of memory. Tried to allocate 31.29 GiB. GPU 0 has a total capacity of 32.00 GiB of which 3.74 GiB is free. Of the allocated memory 25.97 GiB is allocated by PyTorch, and 406.23 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True to avoid fragmentation. See documentation for Memory Management (https://pytorch.org/docs/stable/ ... vironment-variables)
Unloaded DynamicSwap_LlamaModel as complete.
Unloaded CLIPTextModel as complete.
Unloaded SiglipVisionModel as complete.
Unloaded AutoencoderKLHunyuanVideo as complete.
请按任意键继续. . .
发表于 