RuntimeError: cuda runtime error (710) : device-side assert triggered at /pytorch/aten/src/THCUNN/generic/ClassNLLCriterion.cu:110

What about a single tensor throwing the error?`

ipdb> o.shape
torch.Size([16, 46])
ipdb> o.device
device(type='cpu')
ipdb> device
device(type='cuda', index=0)
ipdb> o.to(device, non_blocking=True)
*** RuntimeError: CUDA error: device-side assert triggered
ipdb> list
    245 # Cell
    246 def to_device(b, device=None):
    247     "Recursively put `b` on `device`."
    248     if defaults.use_cuda==False: device='cpu'
    249     elif device is None: device=default_device()
--> 250     def _inner(o): return o.to(device, non_blocking=True) if isinstance(o,Tensor) else o.to_device(device) if hasattr(o, "to_device") else o
    251     return apply(_inner, b)
    252 
    253 # Cell
    254 def to_cpu(b):
    255     "Recursively map lists of tensors in `b ` to the cpu."