CUDA runtime error: an illegal memory access was encountered.
#48
by
qfalex12
- opened
Under input 2000 and output 64, a cuda error occurs when batch_size > 16.
Environment:
nvcr.io/nvidia/pytorch:23.02-py3
A100-SXM4-80GB
Thanks.
Seems like an OOM. It's reasonable since both the seq length and batch size are large.