请问ModelScope显存够了吗，够了的话怎么解决爆显存的问题？

使用vllm部署Qwen2-54B-A14B-Instruct时会出现torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 1.09 GiB. GPU has a total capacity of 22.03 GiB of which 540.88 MiB is free. Including non-PyTorch memory, this process has 21.50 GiB memory in use. Of the allocated memory 20.95 GiB is allocated by PyTorch, and 197.87 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/notes/cuda.html#environment-variables) ，硬件是两张A10，有48G显存，请问ModelScope显存够了吗，够了的话怎么解决爆显存的问题？