Sparsity api_ref

Author: jainapurva

docs/source/api_ref_sparsity.rst

@@ -12,7 +12,7 @@ torchao.sparsity
 
     WandaSparsifier
     PerChannelNormObserver
-    apply_sparse_semi_structured
     apply_fake_sparsity
-
-
+    sparsify_
+    semi_sparse_weight
+    int8_dynamic_activation_int8_semi_sparse_weight

torchao/sparsity/sparse_api.py

@@ -43,7 +43,7 @@ def sparsify_(
     apply_tensor_subclass: Callable[[torch.Tensor], torch.Tensor],
     filter_fn: Optional[Callable[[torch.nn.Module, str], bool]] = None,
 ) -> torch.nn.Module:
-    """Convert the weight of linear modules in the model with `apply_tensor_subclass`
+    """Convert the weight of linear modules in the model with `apply_tensor_subclass`.
     This function is essentially the same as quantize, put for sparsity subclasses.
 
     Currently, we support three options for sparsity:
@@ -57,7 +57,8 @@ def sparsify_(
         filter_fn (Optional[Callable[[torch.nn.Module, str], bool]]): function that takes a nn.Module instance and fully qualified name of the module, returns True if we want to run `apply_tensor_subclass` on
         the weight of the module
 
-    Example::
+    Example:
+    .. code-block:: python
         import torch
         import torch.nn as nn
         from torchao.sparsity import sparsify_