CUDA out of memory. Tried to allocate 128.00 MiB. GPU 0 has a total capacty of 21.99 GiB of which 75.06 MiB is free. Process 4089 has 492.00 MiB memory in use. Process 4086 has 492.00 MiB memory in use. Process 4096 has 492.00 MiB memory in use. Process 4111 has 492.00 MiB memory in use. Process 4108 has 492.00 MiB memory in use. Process 17512 has 2.50 GiB memory in use. Process 21427 has 2.95 GiB memory in use. Process 4963 has 492.00 MiB memory in use. Process 31547 has 2.72 GiB memory in use. Process 7249 has 3.38 GiB memory in use. Process 4869 has 2.66 GiB memory in use. Including non-PyTorch memory, this process has 1.83 GiB memory in use. Process 11274 has 988.00 MiB memory in use. Process 17730 has 988.00 MiB memory in use. Process 26800 has 988.00 MiB memory in use. Of the allocated memory 1.36 GiB is allocated by PyTorch, and 172.33 MiB is reserved by PyTorch but unallocated. If reserved but unallocated memory is large try setting max_split_size_mb to avoid fragmentation.  See documentation for Memory Management and PYTORCH_CUDA_ALLOC_CONF