lix19937
commented
1 month ago 对于 输入为fixed shape，而内部出现 nonzero 操作的一般认为是局部dynamic， currently skipped for dynamic shapes
个人理解：
局部区域按dynamic shape进行优化，而其他fixed shape区域进行常规优化，待验证
cudagraph 的支持可能需要修改init 逻辑
tensor mask op，as example：x = x[x.sum(dim=-1) > 0]
torch.where(condition), as example: torch.where(x>0)
torch.nonzero(x)
https://docs.nvidia.com/deeplearning/tensorrt/sample-support-guide/index.html#sampleNonZeroPlugin