hasattr ConstDictVariable to
from user code:
File "/root/miniforge3/envs/py310-CogVideo/lib/python3.10/site-packages/accelerate/hooks.py", line 165, in new_forward
args, kwargs = module._hf_hook.pre_forward(module, *args, **kwargs)
File "/root/miniforge3/envs/py310-CogVideo/lib/python3.10/site-packages/accelerate/hooks.py", line 364, in pre_forward
return send_to_device(args, self.execution_device), send_to_device(
File "/root/miniforge3/envs/py310-CogVideo/lib/python3.10/site-packages/accelerate/utils/operations.py", line 149, in send_to_device
if is_torch_tensor(tensor) or hasattr(tensor, "to"):
Set TORCH_LOGS="+dynamo" and TORCHDYNAMO_VERBOSE=1 for more information
System Info / 系統信息
Information / 问题信息
Reproduction / 复现过程
on defalut cli_demo.py
运行 之后会在torch._dynamo.exc.py的第221行得到报错
是我的torch.compile用法有问题吗,我想知道你们是怎么使用torch.compile优化性能的。 谢谢🙏
Expected behavior / 期待表现
use torch.compie to speed up cogvideo