Open mayank64ce opened 3 weeks ago
Hey @mayank64ce torch.nn.tils.prun.l1_unstructured
is no longer maintained, so I would recommend using the WeightNormSparsifier
. The sparsifier also allows for more configs, like block_size, or intra block sparsity.
Functionally however, they do the same thing - mask dense models to put zeros in the "right" place.
I see, in the WeightNormSparsifier, there seem to be some additional parameters other different from l1_unstructured. How can I simulate the same behavior for a give prune_ratio
.
Also can this sparse_block_shape
parameter be of any arbitrary shape ?
cc @jcaip