diff --git a/docs/main/_images/RReLU.png b/docs/main/_images/RReLU.png index b0cb8293ba5a..4ea6cd618bca 100644 Binary files a/docs/main/_images/RReLU.png and b/docs/main/_images/RReLU.png differ diff --git a/docs/main/_modules/index.html b/docs/main/_modules/index.html index 5d0baf9e7959..c9e3810c3d73 100644 --- a/docs/main/_modules/index.html +++ b/docs/main/_modules/index.html @@ -242,7 +242,7 @@
- main (2.4.0a0+git31aff29 ) ▼ + main (2.4.0a0+git064a650 ) ▼
diff --git a/docs/main/_modules/torch.html b/docs/main/_modules/torch.html index a1f0e3c56316..6e0b8e4d7273 100644 --- a/docs/main/_modules/torch.html +++ b/docs/main/_modules/torch.html @@ -242,7 +242,7 @@
- main (2.4.0a0+git31aff29 ) ▼ + main (2.4.0a0+git064a650 ) ▼
@@ -2351,8 +2351,8 @@

Source code for torch

 
     """
     _C._log_api_usage_once("torch.compile")
-    if sys.version_info >= (3, 12):
-        raise RuntimeError("Dynamo is not supported on Python 3.12+")
+    if sys.version_info >= (3, 13):
+        raise RuntimeError("Dynamo is not supported on Python 3.13+")
 
     # Decorator mode
     if model is None:
diff --git a/docs/main/_modules/torch/__config__.html b/docs/main/_modules/torch/__config__.html
index 4b766f353b58..cfbbb86e8161 100644
--- a/docs/main/_modules/torch/__config__.html
+++ b/docs/main/_modules/torch/__config__.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/__future__.html b/docs/main/_modules/torch/__future__.html
index 0d3fa717abc1..415229f37856 100644
--- a/docs/main/_modules/torch/__future__.html
+++ b/docs/main/_modules/torch/__future__.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/_jit_internal.html b/docs/main/_modules/torch/_jit_internal.html
index ba556d9ccdd8..f5f6702e91a2 100644
--- a/docs/main/_modules/torch/_jit_internal.html
+++ b/docs/main/_modules/torch/_jit_internal.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
@@ -528,7 +528,6 @@ 
Source code for torch._jit_internal
 from torch._awaits import _Await
 from torch._C import _Await as CAwait, Future as CFuture
 from torch._sources import fake_range, get_source_lines_and_file, parse_def
-from torch._utils_internal import log_torchscript_usage
 from torch.futures import Future
 
 IS_PY39_PLUS: Final[bool] = sys.version_info >= (3, 9)
@@ -1065,7 +1064,6 @@ 
Source code for torch._jit_internal
         # any compiled methods and wasn't decorated with `@torch.jit.export`
         m = torch.jit.script(MyModule())
     """
-    log_torchscript_usage("export")
     fn._torchscript_modifier = FunctionModifiers.EXPORT
     return fn

 
@@ -1107,7 +1105,6 @@ 
Source code for torch._jit_internal
             # exception raised
             m(torch.rand(100))
     """
-    log_torchscript_usage("unused")
     if isinstance(fn, property):
         prop = fn
         setattr(  # noqa: B010
@@ -1195,7 +1192,6 @@ 
Source code for torch._jit_internal
         import os
         os.remove('m.pt')
     """
-    log_torchscript_usage("ignore")
 
     if callable(drop):
         # used without any args, so drop is actually a function
diff --git a/docs/main/_modules/torch/_lobpcg.html b/docs/main/_modules/torch/_lobpcg.html
index 3d59a905bbbe..d73de618d6c4 100644
--- a/docs/main/_modules/torch/_lobpcg.html
+++ b/docs/main/_modules/torch/_lobpcg.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/_logging/_internal.html b/docs/main/_modules/torch/_logging/_internal.html
index 6e03f282689c..c7ee3d940cf9 100644
--- a/docs/main/_modules/torch/_logging/_internal.html
+++ b/docs/main/_modules/torch/_logging/_internal.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/_lowrank.html b/docs/main/_modules/torch/_lowrank.html
index 59a3a1a73aa5..815f15ec2900 100644
--- a/docs/main/_modules/torch/_lowrank.html
+++ b/docs/main/_modules/torch/_lowrank.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/_tensor.html b/docs/main/_modules/torch/_tensor.html
index 9adb2f546940..8260129c7320 100644
--- a/docs/main/_modules/torch/_tensor.html
+++ b/docs/main/_modules/torch/_tensor.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/_tensor_str.html b/docs/main/_modules/torch/_tensor_str.html
index 8e9434ea7831..3df1839304b2 100644
--- a/docs/main/_modules/torch/_tensor_str.html
+++ b/docs/main/_modules/torch/_tensor_str.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/_utils.html b/docs/main/_modules/torch/_utils.html
index 050ffbb7f384..b6326b69ff06 100644
--- a/docs/main/_modules/torch/_utils.html
+++ b/docs/main/_modules/torch/_utils.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/amp/autocast_mode.html b/docs/main/_modules/torch/amp/autocast_mode.html
index 74bd3f0ab580..cd11a423c7ad 100644
--- a/docs/main/_modules/torch/amp/autocast_mode.html
+++ b/docs/main/_modules/torch/amp/autocast_mode.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/intrinsic/modules/fused.html b/docs/main/_modules/torch/ao/nn/intrinsic/modules/fused.html
index 5ef8b1b98524..2d74f88b37fc 100644
--- a/docs/main/_modules/torch/ao/nn/intrinsic/modules/fused.html
+++ b/docs/main/_modules/torch/ao/nn/intrinsic/modules/fused.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/intrinsic/qat/modules/conv_fused.html b/docs/main/_modules/torch/ao/nn/intrinsic/qat/modules/conv_fused.html
index 5b557fb8402b..5dcc4e0c5a7f 100644
--- a/docs/main/_modules/torch/ao/nn/intrinsic/qat/modules/conv_fused.html
+++ b/docs/main/_modules/torch/ao/nn/intrinsic/qat/modules/conv_fused.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/intrinsic/qat/modules/linear_relu.html b/docs/main/_modules/torch/ao/nn/intrinsic/qat/modules/linear_relu.html
index 2bb8c3a2f1e2..17349c4801f8 100644
--- a/docs/main/_modules/torch/ao/nn/intrinsic/qat/modules/linear_relu.html
+++ b/docs/main/_modules/torch/ao/nn/intrinsic/qat/modules/linear_relu.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/intrinsic/quantized/dynamic/modules/linear_relu.html b/docs/main/_modules/torch/ao/nn/intrinsic/quantized/dynamic/modules/linear_relu.html
index 3ace4ddb3cb3..8c1fca4e1d63 100644
--- a/docs/main/_modules/torch/ao/nn/intrinsic/quantized/dynamic/modules/linear_relu.html
+++ b/docs/main/_modules/torch/ao/nn/intrinsic/quantized/dynamic/modules/linear_relu.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/intrinsic/quantized/modules/bn_relu.html b/docs/main/_modules/torch/ao/nn/intrinsic/quantized/modules/bn_relu.html
index 86bc3a277887..a6838ec05f32 100644
--- a/docs/main/_modules/torch/ao/nn/intrinsic/quantized/modules/bn_relu.html
+++ b/docs/main/_modules/torch/ao/nn/intrinsic/quantized/modules/bn_relu.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/intrinsic/quantized/modules/conv_relu.html b/docs/main/_modules/torch/ao/nn/intrinsic/quantized/modules/conv_relu.html
index 164ba8098c88..9cb8d8d0d37a 100644
--- a/docs/main/_modules/torch/ao/nn/intrinsic/quantized/modules/conv_relu.html
+++ b/docs/main/_modules/torch/ao/nn/intrinsic/quantized/modules/conv_relu.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/intrinsic/quantized/modules/linear_relu.html b/docs/main/_modules/torch/ao/nn/intrinsic/quantized/modules/linear_relu.html
index 6bbd9831a057..51b222934e91 100644
--- a/docs/main/_modules/torch/ao/nn/intrinsic/quantized/modules/linear_relu.html
+++ b/docs/main/_modules/torch/ao/nn/intrinsic/quantized/modules/linear_relu.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/qat/dynamic/modules/linear.html b/docs/main/_modules/torch/ao/nn/qat/dynamic/modules/linear.html
index d886797f2162..5534bd34063e 100644
--- a/docs/main/_modules/torch/ao/nn/qat/dynamic/modules/linear.html
+++ b/docs/main/_modules/torch/ao/nn/qat/dynamic/modules/linear.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/qat/modules/conv.html b/docs/main/_modules/torch/ao/nn/qat/modules/conv.html
index 79d91ebc2e6e..57e6442843d3 100644
--- a/docs/main/_modules/torch/ao/nn/qat/modules/conv.html
+++ b/docs/main/_modules/torch/ao/nn/qat/modules/conv.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/qat/modules/linear.html b/docs/main/_modules/torch/ao/nn/qat/modules/linear.html
index 0194784e7792..99db16361b1f 100644
--- a/docs/main/_modules/torch/ao/nn/qat/modules/linear.html
+++ b/docs/main/_modules/torch/ao/nn/qat/modules/linear.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/quantizable/modules/activation.html b/docs/main/_modules/torch/ao/nn/quantizable/modules/activation.html
index acb38b98c45d..c741ba3b7387 100644
--- a/docs/main/_modules/torch/ao/nn/quantizable/modules/activation.html
+++ b/docs/main/_modules/torch/ao/nn/quantizable/modules/activation.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/quantizable/modules/rnn.html b/docs/main/_modules/torch/ao/nn/quantizable/modules/rnn.html
index 68422c63f58a..d21966d71300 100644
--- a/docs/main/_modules/torch/ao/nn/quantizable/modules/rnn.html
+++ b/docs/main/_modules/torch/ao/nn/quantizable/modules/rnn.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/quantized/dynamic/modules/linear.html b/docs/main/_modules/torch/ao/nn/quantized/dynamic/modules/linear.html
index 0d5616637228..04645871a104 100644
--- a/docs/main/_modules/torch/ao/nn/quantized/dynamic/modules/linear.html
+++ b/docs/main/_modules/torch/ao/nn/quantized/dynamic/modules/linear.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/quantized/dynamic/modules/rnn.html b/docs/main/_modules/torch/ao/nn/quantized/dynamic/modules/rnn.html
index 80066ff9833a..b5b8693173dd 100644
--- a/docs/main/_modules/torch/ao/nn/quantized/dynamic/modules/rnn.html
+++ b/docs/main/_modules/torch/ao/nn/quantized/dynamic/modules/rnn.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/quantized/functional.html b/docs/main/_modules/torch/ao/nn/quantized/functional.html
index 135815205977..980203d8409c 100644
--- a/docs/main/_modules/torch/ao/nn/quantized/functional.html
+++ b/docs/main/_modules/torch/ao/nn/quantized/functional.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/quantized/modules/activation.html b/docs/main/_modules/torch/ao/nn/quantized/modules/activation.html
index e37298e72753..a9637a4775ca 100644
--- a/docs/main/_modules/torch/ao/nn/quantized/modules/activation.html
+++ b/docs/main/_modules/torch/ao/nn/quantized/modules/activation.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/quantized/modules/batchnorm.html b/docs/main/_modules/torch/ao/nn/quantized/modules/batchnorm.html
index 5a22c760fe40..b170bdae5972 100644
--- a/docs/main/_modules/torch/ao/nn/quantized/modules/batchnorm.html
+++ b/docs/main/_modules/torch/ao/nn/quantized/modules/batchnorm.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/quantized/modules/conv.html b/docs/main/_modules/torch/ao/nn/quantized/modules/conv.html
index d8e7280f1bec..ebb60ad685d1 100644
--- a/docs/main/_modules/torch/ao/nn/quantized/modules/conv.html
+++ b/docs/main/_modules/torch/ao/nn/quantized/modules/conv.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/quantized/modules/embedding_ops.html b/docs/main/_modules/torch/ao/nn/quantized/modules/embedding_ops.html
index c548feeddce6..d3d4dd5bb7a9 100644
--- a/docs/main/_modules/torch/ao/nn/quantized/modules/embedding_ops.html
+++ b/docs/main/_modules/torch/ao/nn/quantized/modules/embedding_ops.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/quantized/modules/functional_modules.html b/docs/main/_modules/torch/ao/nn/quantized/modules/functional_modules.html
index fb4b4320b66e..cbcf2550f38f 100644
--- a/docs/main/_modules/torch/ao/nn/quantized/modules/functional_modules.html
+++ b/docs/main/_modules/torch/ao/nn/quantized/modules/functional_modules.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/quantized/modules/linear.html b/docs/main/_modules/torch/ao/nn/quantized/modules/linear.html
index da690c2b211c..13840cdf698d 100644
--- a/docs/main/_modules/torch/ao/nn/quantized/modules/linear.html
+++ b/docs/main/_modules/torch/ao/nn/quantized/modules/linear.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/nn/quantized/modules/normalization.html b/docs/main/_modules/torch/ao/nn/quantized/modules/normalization.html
index d33590836545..fd770989bccc 100644
--- a/docs/main/_modules/torch/ao/nn/quantized/modules/normalization.html
+++ b/docs/main/_modules/torch/ao/nn/quantized/modules/normalization.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/ns/_numeric_suite.html b/docs/main/_modules/torch/ao/ns/_numeric_suite.html
index cb66ba46cb84..0a1a8c49d2c5 100644
--- a/docs/main/_modules/torch/ao/ns/_numeric_suite.html
+++ b/docs/main/_modules/torch/ao/ns/_numeric_suite.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/ns/_numeric_suite_fx.html b/docs/main/_modules/torch/ao/ns/_numeric_suite_fx.html
index e5e454728503..3e9ff093a171 100644
--- a/docs/main/_modules/torch/ao/ns/_numeric_suite_fx.html
+++ b/docs/main/_modules/torch/ao/ns/_numeric_suite_fx.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/ns/fx/utils.html b/docs/main/_modules/torch/ao/ns/fx/utils.html
index 16964a0d9928..1a3ab3496fcb 100644
--- a/docs/main/_modules/torch/ao/ns/fx/utils.html
+++ b/docs/main/_modules/torch/ao/ns/fx/utils.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/quantization.html b/docs/main/_modules/torch/ao/quantization.html
index e90f5d418ae5..ef07de4be82f 100644
--- a/docs/main/_modules/torch/ao/quantization.html
+++ b/docs/main/_modules/torch/ao/quantization.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/quantization/backend_config/backend_config.html b/docs/main/_modules/torch/ao/quantization/backend_config/backend_config.html
index 9b0022274120..1e12e326cc69 100644
--- a/docs/main/_modules/torch/ao/quantization/backend_config/backend_config.html
+++ b/docs/main/_modules/torch/ao/quantization/backend_config/backend_config.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/quantization/fake_quantize.html b/docs/main/_modules/torch/ao/quantization/fake_quantize.html
index 5003138a1a8b..11bfcf08279f 100644
--- a/docs/main/_modules/torch/ao/quantization/fake_quantize.html
+++ b/docs/main/_modules/torch/ao/quantization/fake_quantize.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/quantization/fuse_modules.html b/docs/main/_modules/torch/ao/quantization/fuse_modules.html
index 282a93167e58..a9deddbaffd9 100644
--- a/docs/main/_modules/torch/ao/quantization/fuse_modules.html
+++ b/docs/main/_modules/torch/ao/quantization/fuse_modules.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/quantization/fx/custom_config.html b/docs/main/_modules/torch/ao/quantization/fx/custom_config.html
index f5f1594b6bef..247e775f4cb5 100644
--- a/docs/main/_modules/torch/ao/quantization/fx/custom_config.html
+++ b/docs/main/_modules/torch/ao/quantization/fx/custom_config.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/quantization/observer.html b/docs/main/_modules/torch/ao/quantization/observer.html
index f807fff1aeb6..f0f17c9ba193 100644
--- a/docs/main/_modules/torch/ao/quantization/observer.html
+++ b/docs/main/_modules/torch/ao/quantization/observer.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/quantization/pt2e/export_utils.html b/docs/main/_modules/torch/ao/quantization/pt2e/export_utils.html
index 579508c37794..128a7788c0ea 100644
--- a/docs/main/_modules/torch/ao/quantization/pt2e/export_utils.html
+++ b/docs/main/_modules/torch/ao/quantization/pt2e/export_utils.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/quantization/qconfig.html b/docs/main/_modules/torch/ao/quantization/qconfig.html
index 6e7ee439ee2e..7836a4bfd8b6 100644
--- a/docs/main/_modules/torch/ao/quantization/qconfig.html
+++ b/docs/main/_modules/torch/ao/quantization/qconfig.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/quantization/qconfig_mapping.html b/docs/main/_modules/torch/ao/quantization/qconfig_mapping.html
index aa111a034038..16f9fd6dc848 100644
--- a/docs/main/_modules/torch/ao/quantization/qconfig_mapping.html
+++ b/docs/main/_modules/torch/ao/quantization/qconfig_mapping.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/quantization/quantize.html b/docs/main/_modules/torch/ao/quantization/quantize.html
index 88c4ddea35dc..cf2b198fab55 100644
--- a/docs/main/_modules/torch/ao/quantization/quantize.html
+++ b/docs/main/_modules/torch/ao/quantization/quantize.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/quantization/quantize_fx.html b/docs/main/_modules/torch/ao/quantization/quantize_fx.html
index 3a98e7704252..572eb7f4a01b 100644
--- a/docs/main/_modules/torch/ao/quantization/quantize_fx.html
+++ b/docs/main/_modules/torch/ao/quantization/quantize_fx.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/ao/quantization/stubs.html b/docs/main/_modules/torch/ao/quantization/stubs.html
index 0cc1988c15a3..19df115bc67d 100644
--- a/docs/main/_modules/torch/ao/quantization/stubs.html
+++ b/docs/main/_modules/torch/ao/quantization/stubs.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/autograd.html b/docs/main/_modules/torch/autograd.html
index 3817741b48f0..51f769c88075 100644
--- a/docs/main/_modules/torch/autograd.html
+++ b/docs/main/_modules/torch/autograd.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/autograd/anomaly_mode.html b/docs/main/_modules/torch/autograd/anomaly_mode.html
index d34efcbc141c..e67a22e05133 100644
--- a/docs/main/_modules/torch/autograd/anomaly_mode.html
+++ b/docs/main/_modules/torch/autograd/anomaly_mode.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/autograd/forward_ad.html b/docs/main/_modules/torch/autograd/forward_ad.html
index c2efd8fb3fee..4a8da542e819 100644
--- a/docs/main/_modules/torch/autograd/forward_ad.html
+++ b/docs/main/_modules/torch/autograd/forward_ad.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/autograd/function.html b/docs/main/_modules/torch/autograd/function.html
index 175cea103b26..feee72b30814 100644
--- a/docs/main/_modules/torch/autograd/function.html
+++ b/docs/main/_modules/torch/autograd/function.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/autograd/functional.html b/docs/main/_modules/torch/autograd/functional.html
index 6a507a877026..0a62dc33c469 100644
--- a/docs/main/_modules/torch/autograd/functional.html
+++ b/docs/main/_modules/torch/autograd/functional.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/autograd/grad_mode.html b/docs/main/_modules/torch/autograd/grad_mode.html
index 32e13d49c2db..20cbe1b99f0c 100644
--- a/docs/main/_modules/torch/autograd/grad_mode.html
+++ b/docs/main/_modules/torch/autograd/grad_mode.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/autograd/gradcheck.html b/docs/main/_modules/torch/autograd/gradcheck.html
index 17c01f610d1a..762e84d3cf81 100644
--- a/docs/main/_modules/torch/autograd/gradcheck.html
+++ b/docs/main/_modules/torch/autograd/gradcheck.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/autograd/graph.html b/docs/main/_modules/torch/autograd/graph.html
index 15924d8da4e8..74b20b4ccb1e 100644
--- a/docs/main/_modules/torch/autograd/graph.html
+++ b/docs/main/_modules/torch/autograd/graph.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/autograd/profiler.html b/docs/main/_modules/torch/autograd/profiler.html
index a896d07cde86..1d935ef9a94e 100644
--- a/docs/main/_modules/torch/autograd/profiler.html
+++ b/docs/main/_modules/torch/autograd/profiler.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/autograd/profiler_util.html b/docs/main/_modules/torch/autograd/profiler_util.html
index c96af38f75fe..67f1a034b5e3 100644
--- a/docs/main/_modules/torch/autograd/profiler_util.html
+++ b/docs/main/_modules/torch/autograd/profiler_util.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/backends/cpu.html b/docs/main/_modules/torch/backends/cpu.html
index 009ea66b724b..cc56ab957c67 100644
--- a/docs/main/_modules/torch/backends/cpu.html
+++ b/docs/main/_modules/torch/backends/cpu.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/backends/cuda.html b/docs/main/_modules/torch/backends/cuda.html
index 4db12ab08cbd..a9e129baa77e 100644
--- a/docs/main/_modules/torch/backends/cuda.html
+++ b/docs/main/_modules/torch/backends/cuda.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/backends/cudnn.html b/docs/main/_modules/torch/backends/cudnn.html
index 02a7fc484183..4401de81c01e 100644
--- a/docs/main/_modules/torch/backends/cudnn.html
+++ b/docs/main/_modules/torch/backends/cudnn.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/backends/mha.html b/docs/main/_modules/torch/backends/mha.html
index 35834ff52996..52a740c13587 100644
--- a/docs/main/_modules/torch/backends/mha.html
+++ b/docs/main/_modules/torch/backends/mha.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/backends/mkl.html b/docs/main/_modules/torch/backends/mkl.html
index 16216cd3cf65..87f8ff2fb004 100644
--- a/docs/main/_modules/torch/backends/mkl.html
+++ b/docs/main/_modules/torch/backends/mkl.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/backends/mkldnn.html b/docs/main/_modules/torch/backends/mkldnn.html
index bcf3bdd59bea..22fc5d0ab181 100644
--- a/docs/main/_modules/torch/backends/mkldnn.html
+++ b/docs/main/_modules/torch/backends/mkldnn.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/backends/mps.html b/docs/main/_modules/torch/backends/mps.html
index 389629484750..d113bde79860 100644
--- a/docs/main/_modules/torch/backends/mps.html
+++ b/docs/main/_modules/torch/backends/mps.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/backends/nnpack.html b/docs/main/_modules/torch/backends/nnpack.html
index 6551523ef244..6163e640dc59 100644
--- a/docs/main/_modules/torch/backends/nnpack.html
+++ b/docs/main/_modules/torch/backends/nnpack.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/backends/openmp.html b/docs/main/_modules/torch/backends/openmp.html
index 9c1725d24eb9..e26b7b6e6843 100644
--- a/docs/main/_modules/torch/backends/openmp.html
+++ b/docs/main/_modules/torch/backends/openmp.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/backends/opt_einsum.html b/docs/main/_modules/torch/backends/opt_einsum.html
index 84d3dea2efb7..83d99edc8aa0 100644
--- a/docs/main/_modules/torch/backends/opt_einsum.html
+++ b/docs/main/_modules/torch/backends/opt_einsum.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/compiler.html b/docs/main/_modules/torch/compiler.html
index 4badf7b964c7..a02678b65824 100644
--- a/docs/main/_modules/torch/compiler.html
+++ b/docs/main/_modules/torch/compiler.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/cpu.html b/docs/main/_modules/torch/cpu.html
index c8ea047cc796..5a15ba9d7c25 100644
--- a/docs/main/_modules/torch/cpu.html
+++ b/docs/main/_modules/torch/cpu.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/cpu/amp/autocast_mode.html b/docs/main/_modules/torch/cpu/amp/autocast_mode.html
index d9233c390ce4..d4c4eba95d66 100644
--- a/docs/main/_modules/torch/cpu/amp/autocast_mode.html
+++ b/docs/main/_modules/torch/cpu/amp/autocast_mode.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/cuda.html b/docs/main/_modules/torch/cuda.html
index b5142bab4638..8258281e1c7f 100644
--- a/docs/main/_modules/torch/cuda.html
+++ b/docs/main/_modules/torch/cuda.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/cuda/_sanitizer.html b/docs/main/_modules/torch/cuda/_sanitizer.html
index 433ddc7d66d9..351ceb4ea084 100644
--- a/docs/main/_modules/torch/cuda/_sanitizer.html
+++ b/docs/main/_modules/torch/cuda/_sanitizer.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/cuda/amp/autocast_mode.html b/docs/main/_modules/torch/cuda/amp/autocast_mode.html
index c44da641afcf..bb9ffccd8eaa 100644
--- a/docs/main/_modules/torch/cuda/amp/autocast_mode.html
+++ b/docs/main/_modules/torch/cuda/amp/autocast_mode.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/cuda/amp/grad_scaler.html b/docs/main/_modules/torch/cuda/amp/grad_scaler.html
index 7dfd0ce33c7b..f5205cdce37c 100644
--- a/docs/main/_modules/torch/cuda/amp/grad_scaler.html
+++ b/docs/main/_modules/torch/cuda/amp/grad_scaler.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/cuda/graphs.html b/docs/main/_modules/torch/cuda/graphs.html
index 0df8b8b47f15..adb6b3e40ac8 100644
--- a/docs/main/_modules/torch/cuda/graphs.html
+++ b/docs/main/_modules/torch/cuda/graphs.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/cuda/jiterator.html b/docs/main/_modules/torch/cuda/jiterator.html
index c2a9256409c6..e3ad27a671a0 100644
--- a/docs/main/_modules/torch/cuda/jiterator.html
+++ b/docs/main/_modules/torch/cuda/jiterator.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/cuda/memory.html b/docs/main/_modules/torch/cuda/memory.html
index 10ce966f9451..b940f5823ecf 100644
--- a/docs/main/_modules/torch/cuda/memory.html
+++ b/docs/main/_modules/torch/cuda/memory.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/cuda/nvtx.html b/docs/main/_modules/torch/cuda/nvtx.html
index e6d4f5dc61e5..a4adee89fdff 100644
--- a/docs/main/_modules/torch/cuda/nvtx.html
+++ b/docs/main/_modules/torch/cuda/nvtx.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/cuda/random.html b/docs/main/_modules/torch/cuda/random.html
index 9efad70db448..22871a499610 100644
--- a/docs/main/_modules/torch/cuda/random.html
+++ b/docs/main/_modules/torch/cuda/random.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/cuda/streams.html b/docs/main/_modules/torch/cuda/streams.html
index e0defd0d8dda..915b678d0167 100644
--- a/docs/main/_modules/torch/cuda/streams.html
+++ b/docs/main/_modules/torch/cuda/streams.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed.html b/docs/main/_modules/torch/distributed.html
index 86f0d7843955..a9cf86b5ee6d 100644
--- a/docs/main/_modules/torch/distributed.html
+++ b/docs/main/_modules/torch/distributed.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/algorithms/ddp_comm_hooks/debugging_hooks.html b/docs/main/_modules/torch/distributed/algorithms/ddp_comm_hooks/debugging_hooks.html
index a560ba6d17c9..1b6c61727f44 100644
--- a/docs/main/_modules/torch/distributed/algorithms/ddp_comm_hooks/debugging_hooks.html
+++ b/docs/main/_modules/torch/distributed/algorithms/ddp_comm_hooks/debugging_hooks.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.html b/docs/main/_modules/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.html
index ee6ba408867b..ae79e14fd1ce 100644
--- a/docs/main/_modules/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.html
+++ b/docs/main/_modules/torch/distributed/algorithms/ddp_comm_hooks/default_hooks.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.html b/docs/main/_modules/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.html
index 7ce894f0f057..e053feff794a 100644
--- a/docs/main/_modules/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.html
+++ b/docs/main/_modules/torch/distributed/algorithms/ddp_comm_hooks/powerSGD_hook.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/algorithms/join.html b/docs/main/_modules/torch/distributed/algorithms/join.html
index be896b837fb0..dd9af835f838 100644
--- a/docs/main/_modules/torch/distributed/algorithms/join.html
+++ b/docs/main/_modules/torch/distributed/algorithms/join.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/autograd.html b/docs/main/_modules/torch/distributed/autograd.html
index 37c1731009b2..2877b8df1de2 100644
--- a/docs/main/_modules/torch/distributed/autograd.html
+++ b/docs/main/_modules/torch/distributed/autograd.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/checkpoint/default_planner.html b/docs/main/_modules/torch/distributed/checkpoint/default_planner.html
index ee0f1a332100..664d35354aff 100644
--- a/docs/main/_modules/torch/distributed/checkpoint/default_planner.html
+++ b/docs/main/_modules/torch/distributed/checkpoint/default_planner.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/checkpoint/filesystem.html b/docs/main/_modules/torch/distributed/checkpoint/filesystem.html
index e97034a8b5ab..f41eca2f1adf 100644
--- a/docs/main/_modules/torch/distributed/checkpoint/filesystem.html
+++ b/docs/main/_modules/torch/distributed/checkpoint/filesystem.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/checkpoint/format_utils.html b/docs/main/_modules/torch/distributed/checkpoint/format_utils.html
index 0d34715be020..c827fdbdc71e 100644
--- a/docs/main/_modules/torch/distributed/checkpoint/format_utils.html
+++ b/docs/main/_modules/torch/distributed/checkpoint/format_utils.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/checkpoint/planner.html b/docs/main/_modules/torch/distributed/checkpoint/planner.html
index b63fa8cfba46..0381b2f0e6df 100644
--- a/docs/main/_modules/torch/distributed/checkpoint/planner.html
+++ b/docs/main/_modules/torch/distributed/checkpoint/planner.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/checkpoint/state_dict.html b/docs/main/_modules/torch/distributed/checkpoint/state_dict.html
index 206266923557..d4f1260fca70 100644
--- a/docs/main/_modules/torch/distributed/checkpoint/state_dict.html
+++ b/docs/main/_modules/torch/distributed/checkpoint/state_dict.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/checkpoint/state_dict_loader.html b/docs/main/_modules/torch/distributed/checkpoint/state_dict_loader.html
index b63e71d3750e..55d796da3949 100644
--- a/docs/main/_modules/torch/distributed/checkpoint/state_dict_loader.html
+++ b/docs/main/_modules/torch/distributed/checkpoint/state_dict_loader.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/checkpoint/state_dict_saver.html b/docs/main/_modules/torch/distributed/checkpoint/state_dict_saver.html
index 11c20205c4ce..21dc08bfa57d 100644
--- a/docs/main/_modules/torch/distributed/checkpoint/state_dict_saver.html
+++ b/docs/main/_modules/torch/distributed/checkpoint/state_dict_saver.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/checkpoint/stateful.html b/docs/main/_modules/torch/distributed/checkpoint/stateful.html
index 3f98a58ecb3b..2a33769740a2 100644
--- a/docs/main/_modules/torch/distributed/checkpoint/stateful.html
+++ b/docs/main/_modules/torch/distributed/checkpoint/stateful.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/checkpoint/storage.html b/docs/main/_modules/torch/distributed/checkpoint/storage.html
index 85d140a0764a..c819895d2a44 100644
--- a/docs/main/_modules/torch/distributed/checkpoint/storage.html
+++ b/docs/main/_modules/torch/distributed/checkpoint/storage.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/device_mesh.html b/docs/main/_modules/torch/distributed/device_mesh.html
index 8a2e8a8dbefa..af6738044bcd 100644
--- a/docs/main/_modules/torch/distributed/device_mesh.html
+++ b/docs/main/_modules/torch/distributed/device_mesh.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/distributed_c10d.html b/docs/main/_modules/torch/distributed/distributed_c10d.html
index 4bef30a254d4..3a2da5ef72ef 100644
--- a/docs/main/_modules/torch/distributed/distributed_c10d.html
+++ b/docs/main/_modules/torch/distributed/distributed_c10d.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/agent/server/api.html b/docs/main/_modules/torch/distributed/elastic/agent/server/api.html
index 38e714705052..e5feafc48225 100644
--- a/docs/main/_modules/torch/distributed/elastic/agent/server/api.html
+++ b/docs/main/_modules/torch/distributed/elastic/agent/server/api.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/agent/server/local_elastic_agent.html b/docs/main/_modules/torch/distributed/elastic/agent/server/local_elastic_agent.html
index f1f46559b6b6..a1432ec50f7f 100644
--- a/docs/main/_modules/torch/distributed/elastic/agent/server/local_elastic_agent.html
+++ b/docs/main/_modules/torch/distributed/elastic/agent/server/local_elastic_agent.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/events.html b/docs/main/_modules/torch/distributed/elastic/events.html
index 80fd7bdcb6fd..fee99c903cb4 100644
--- a/docs/main/_modules/torch/distributed/elastic/events.html
+++ b/docs/main/_modules/torch/distributed/elastic/events.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/events/api.html b/docs/main/_modules/torch/distributed/elastic/events/api.html
index bed8b0350bc6..5a7ad77200d9 100644
--- a/docs/main/_modules/torch/distributed/elastic/events/api.html
+++ b/docs/main/_modules/torch/distributed/elastic/events/api.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/events/handlers.html b/docs/main/_modules/torch/distributed/elastic/events/handlers.html
index d20113399e3d..eac60a462f5f 100644
--- a/docs/main/_modules/torch/distributed/elastic/events/handlers.html
+++ b/docs/main/_modules/torch/distributed/elastic/events/handlers.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/metrics/api.html b/docs/main/_modules/torch/distributed/elastic/metrics/api.html
index 55a937c07fea..43aa81807901 100644
--- a/docs/main/_modules/torch/distributed/elastic/metrics/api.html
+++ b/docs/main/_modules/torch/distributed/elastic/metrics/api.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/multiprocessing.html b/docs/main/_modules/torch/distributed/elastic/multiprocessing.html
index bf5f8b0cc49e..dcf48e4f4958 100644
--- a/docs/main/_modules/torch/distributed/elastic/multiprocessing.html
+++ b/docs/main/_modules/torch/distributed/elastic/multiprocessing.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/multiprocessing/api.html b/docs/main/_modules/torch/distributed/elastic/multiprocessing/api.html
index e05cf970efd1..0ae1da199f0e 100644
--- a/docs/main/_modules/torch/distributed/elastic/multiprocessing/api.html
+++ b/docs/main/_modules/torch/distributed/elastic/multiprocessing/api.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/multiprocessing/errors.html b/docs/main/_modules/torch/distributed/elastic/multiprocessing/errors.html
index 3985c588a168..a9cd633dc48f 100644
--- a/docs/main/_modules/torch/distributed/elastic/multiprocessing/errors.html
+++ b/docs/main/_modules/torch/distributed/elastic/multiprocessing/errors.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/multiprocessing/errors/error_handler.html b/docs/main/_modules/torch/distributed/elastic/multiprocessing/errors/error_handler.html
index 943359c51c24..50eab90aad1e 100644
--- a/docs/main/_modules/torch/distributed/elastic/multiprocessing/errors/error_handler.html
+++ b/docs/main/_modules/torch/distributed/elastic/multiprocessing/errors/error_handler.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/multiprocessing/subprocess_handler/handlers.html b/docs/main/_modules/torch/distributed/elastic/multiprocessing/subprocess_handler/handlers.html
index 38e7ad695416..85f079608b6e 100644
--- a/docs/main/_modules/torch/distributed/elastic/multiprocessing/subprocess_handler/handlers.html
+++ b/docs/main/_modules/torch/distributed/elastic/multiprocessing/subprocess_handler/handlers.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/multiprocessing/subprocess_handler/subprocess_handler.html b/docs/main/_modules/torch/distributed/elastic/multiprocessing/subprocess_handler/subprocess_handler.html
index 6514c1993510..4c1de689cb16 100644
--- a/docs/main/_modules/torch/distributed/elastic/multiprocessing/subprocess_handler/subprocess_handler.html
+++ b/docs/main/_modules/torch/distributed/elastic/multiprocessing/subprocess_handler/subprocess_handler.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/rendezvous/api.html b/docs/main/_modules/torch/distributed/elastic/rendezvous/api.html
index 0d082aec057c..4d4d40bae6fa 100644
--- a/docs/main/_modules/torch/distributed/elastic/rendezvous/api.html
+++ b/docs/main/_modules/torch/distributed/elastic/rendezvous/api.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.html b/docs/main/_modules/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.html
index f283982372fe..a86c31771ab5 100644
--- a/docs/main/_modules/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.html
+++ b/docs/main/_modules/torch/distributed/elastic/rendezvous/c10d_rendezvous_backend.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/rendezvous/dynamic_rendezvous.html b/docs/main/_modules/torch/distributed/elastic/rendezvous/dynamic_rendezvous.html
index 889085d8f55b..d0c135b0f808 100644
--- a/docs/main/_modules/torch/distributed/elastic/rendezvous/dynamic_rendezvous.html
+++ b/docs/main/_modules/torch/distributed/elastic/rendezvous/dynamic_rendezvous.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_rendezvous.html b/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_rendezvous.html
index 46ea4fa58d10..f1e2ea8e0bf7 100644
--- a/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_rendezvous.html
+++ b/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_rendezvous.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_rendezvous_backend.html b/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_rendezvous_backend.html
index b136ebaceb4b..b6eee01ca8d1 100644
--- a/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_rendezvous_backend.html
+++ b/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_rendezvous_backend.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_server.html b/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_server.html
index 0c350d611f04..54ab8c6d23ac 100644
--- a/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_server.html
+++ b/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_server.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_store.html b/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_store.html
index 34bbff1ee8b7..9ffa3657a025 100644
--- a/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_store.html
+++ b/docs/main/_modules/torch/distributed/elastic/rendezvous/etcd_store.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/timer/api.html b/docs/main/_modules/torch/distributed/elastic/timer/api.html
index bcafada481d1..0caf5726716b 100644
--- a/docs/main/_modules/torch/distributed/elastic/timer/api.html
+++ b/docs/main/_modules/torch/distributed/elastic/timer/api.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/timer/file_based_local_timer.html b/docs/main/_modules/torch/distributed/elastic/timer/file_based_local_timer.html
index 6c9d81f6e6a4..feea2017ab44 100644
--- a/docs/main/_modules/torch/distributed/elastic/timer/file_based_local_timer.html
+++ b/docs/main/_modules/torch/distributed/elastic/timer/file_based_local_timer.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/elastic/timer/local_timer.html b/docs/main/_modules/torch/distributed/elastic/timer/local_timer.html
index f92d3d98d513..81a362bd1dd7 100644
--- a/docs/main/_modules/torch/distributed/elastic/timer/local_timer.html
+++ b/docs/main/_modules/torch/distributed/elastic/timer/local_timer.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/fsdp/api.html b/docs/main/_modules/torch/distributed/fsdp/api.html
index e16e9444ab38..84ff2d8f19e2 100644
--- a/docs/main/_modules/torch/distributed/fsdp/api.html
+++ b/docs/main/_modules/torch/distributed/fsdp/api.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/fsdp/fully_sharded_data_parallel.html b/docs/main/_modules/torch/distributed/fsdp/fully_sharded_data_parallel.html
index 66945f93cdd9..8153de593aa6 100644
--- a/docs/main/_modules/torch/distributed/fsdp/fully_sharded_data_parallel.html
+++ b/docs/main/_modules/torch/distributed/fsdp/fully_sharded_data_parallel.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
@@ -584,7 +584,7 @@ 
Source code for torch.distributed.fsdp.fully_sharded_data_parallel
_register_flat_param,
     _register_orig_params,
     _unshard_params,
-    _unshard_params_recurse,
+    _unshard_params_for_summon,
 )
 from .wrap import CustomPolicy, ModuleWrapPolicy
 
@@ -614,7 +614,8 @@ 
Source code for torch.distributed.fsdp.fully_sharded_data_parallel
    .. _`Xu et al.`: https://arxiv.org/abs/2004.13336
     .. _DeepSpeed: https://www.deepspeed.ai/
 
-    For advanced notes please refer to :ref:`fsdp_notes`.
+    To understand FSDP internals, refer to the
+    :ref:`fsdp_notes`.
 
     Example::
 
@@ -629,111 +630,91 @@ 
Source code for torch.distributed.fsdp.fully_sharded_data_parallel
        >>> loss.backward()
         >>> optim.step()
 
-    .. warning::
-        The optimizer must be initialized *after* the module has been wrapped
-        with FSDP since FSDP will shard and transform the module's parameters
-        in a way that may not preserve the original parameter variables. Thus,
-        the previously initialized optimizer may have stale references to the
-        parameters.
-
-    .. warning::
-        If the destination CUDA device has ID ``dev_id``, either (1)
-        ``module`` should already be placed on that device, (2) the device
-        should be set using ``torch.cuda.set_device(dev_id)``, or (3)
-        ``dev_id`` should be passed into the ``device_id`` constructor
-        argument. This FSDP instance's compute device will be that destination
-        device. For (1) and (3), the FSDP initialization always occurs on GPU.
-        For (2), the FSDP initialization happens on ``module`` 's current
-        device, which may be CPU.
-
-    .. warning::
-        FSDP currently does not support gradient accumulation outside
-        ``no_sync()`` when using CPU offloading. Trying to do so yields
-        incorrect results since FSDP will use the newly-reduced gradient
-        instead of accumulating with any existing gradient.
-
-    .. warning::
-        Changing the original parameter variable names after construction will
-        lead to undefined behavior.
-
-    .. warning::
-        Passing in the ``sync_module_states=True`` flag requires ``module`` to
-        be on GPU or to use the ``device_id`` argument to specify a CUDA device
-        that FSDP will move ``module`` to in the FSDP constructor. This is
-        because ``sync_module_states=True`` requires GPU communication.
-
-    .. warning::
-        As of PyTorch 1.12, FSDP only offers limited support for shared parameters
-        (for example, setting one ``Linear`` layer's weight to another's). In
-        particular, modules that share parameters must be wrapped as part of the
-        same FSDP unit. If enhanced shared parameter support is needed for your
-        use case, please ping https://github.com/pytorch/pytorch/issues/77724
-
-    .. warning::
-        FSDP has some constraints on freezing parameters (i.e. setting
-        ``param.requires_grad=False``). For ``use_orig_params=False``, each
-        FSDP instance must manage parameters that are all frozen or all
-        non-frozen. For ``use_orig_params=True``, FSDP supports mixing frozen
-        and non-frozen, but we recommend not doing so since then the gradient
-        memory usage will be higher than expected (namely, equivalent to not
-        freezing those parameters). This means that ideally, frozen parameters
-        should be isolated into their own ``nn.Module`` s and wrapped
-        separately with FSDP.
-
-    .. note::
-        Attempting to run the forward pass of a submodule that is contained in an
-        FSDP instance is not supported and will result in errors. This is because the
-        submodule's parameters will be sharded, but it itself is not an FSDP instance,
-        so its forward pass will not all-gather the full parameters appropriately.
-        This could potentially happen when attempting to run only the encoder of a
-        encoder-decoder model, and the encoder is not wrapped in its own FSDP instance. To
-        resolve this, please wrap the submodule in its own FSDP unit.
-
-    .. note::
-        FSDP moves input tensors to the ``forward`` method to the GPU compute
-        device, so the user does not need to manually move them from CPU.
-
-    .. warning::
-        The user should not modify the parameters between forward and backward
-        without using the :meth:`summon_full_params` context since the
-        modifications may not persist. Moreover, for ``use_orig_params=False``,
-        accessing the original parameters between forward and backward may
-        raise an illegal memory access.
-
-    .. warning::
-        For ``use_orig_params=True``, ``ShardingStrategy.SHARD_GRAD_OP``
-        exposes the unsharded parameters, not the sharded parameters, after
-        forward since it does not free the unsharded ones, unlike
-        ``ShardingStrategy.FULL_SHARD``. One caveat is that, since gradients
-        are always sharded or ``None``, ``ShardingStrategy.SHARD_GRAD_OP`` will
-        not expose the sharded gradients with the unsharded parameters after
-        forward. If you want to inspect the gradients, try
-        :meth:`summon_full_params` with ``with_grads=True``.
-
-    .. warning::
-        FSDP replaces managed modules' parameters with ``torch.Tensor`` views
-        during forward and backward computation for autograd-related reasons.
-        If your module's forward relies on saved references to the parameters
-        instead of reacquiring the references each iteration, then it will not
-        see FSDP's newly created views, and autograd will not work correctly.
-
-    .. note::
-        With ``limit_all_gathers=True``, you may see a gap in the FSDP
-        pre-forward where the CPU thread is not issuing any kernels. This is
-        intentional and shows the rate limiter in effect. Synchronizing the CPU
-        thread in that way prevents over-allocating memory for subsequent
-        all-gathers, and it should not actually delay GPU kernel execution.
-
-    .. note::
-        When using ``sharding_strategy=ShardingStrategy.HYBRID_SHARD`` with the
-        sharding process group being intra-node and the replication process
-        group being inter-node, setting ``NCCL_CROSS_NIC=1`` can help improve
-        the all-reduce times over the replication process group for some
-        cluster setups.
-
-    .. warning::
-        FSDP does not work with double backwards due to how it registers
-        backward hooks.
+    Using FSDP involves wrapping your module and then initializing your
+    optimizer after. This is required since FSDP changes the parameter
+    variables.
+
+    When setting up FSDP, you need to consider the destination CUDA
+    device. If the device has an ID (``dev_id``), you have three options:
+
+    * Place the module on that device
+    * Set the device using ``torch.cuda.set_device(dev_id)``
+    * Pass ``dev_id`` into the ``device_id`` constructor argument.
+
+    This ensures that the FSDP instance's compute device is the
+    destination device. For option 1 and 3, the FSDP initialization
+    always occurs on GPU. For option 2, the FSDP initialization
+    happens on module's current device, which may be a CPU.
+
+    If you're using the ``sync_module_states=True`` flag, you need to
+    ensure that the module is on a GPU or use the ``device_id``
+    argument to specify a CUDA device that FSDP will move the module
+    to in the FSDP constructor. This is necessary because
+    ``sync_module_states=True`` requires GPU communication.
+
+    FSDP also takes care of moving input tensors to the forward method
+    to the GPU compute device, so you don't need to manually move them
+    from CPU.
+
+    For ``use_orig_params=True``,
+    ``ShardingStrategy.SHARD_GRAD_OP`` exposes the unsharded
+    parameters, not the sharded parameters after forward, unlike
+    ``ShardingStrategy.FULL_SHARD``. If you want
+    to inspect the gradients, you can use the ``summon_full_params``
+    method with ``with_grads=True``.
+
+    With ``limit_all_gathers=True``, you may see a gap in the FSDP
+    pre-forward where the CPU thread is not issuing any kernels. This is
+    intentional and shows the rate limiter in effect. Synchronizing the CPU
+    thread in that way prevents over-allocating memory for subsequent
+    all-gathers, and it should not actually delay GPU kernel execution.
+
+    FSDP replaces managed modules' parameters with ``torch.Tensor``
+    views during forward and backward computation for autograd-related
+    reasons. If your module's forward relies on saved references to
+    the parameters instead of reacquiring the references each
+    iteration, then it will not see FSDP's newly created views,
+    and autograd will not work correctly.
+
+    Finally, when using ``sharding_strategy=ShardingStrategy.HYBRID_SHARD``
+    with the sharding process group being intra-node and the
+    replication process group being inter-node, setting
+    ``NCCL_CROSS_NIC=1`` can help improve the all-reduce times over
+    the replication process group for some cluster setups.
+
+    **Limitations**
+
+    There are several limitations to be aware of when using FSDP:
+
+    * FSDP currently does not support gradient accumulation outside
+      ``no_sync()`` when using CPU offloading. This is because FSDP
+      uses the newly-reduced gradient instead of accumulating with any
+      existing gradient, which can lead to incorrect results.
+
+    * FSDP does not support running the forward pass of a submodule
+      that is contained in an FSDP instance. This is because the
+      submodule's parameters will be sharded, but the submodule itself
+      is not an FSDP instance, so its forward pass will not all-gather
+      the full parameters appropriately.
+
+    * FSDP does not work with double backwards due to the way it
+      registers backward hooks.
+
+    * FSDP has some constraints when freezing parameters.
+      For ``use_orig_params=False``, each FSDP instance must manage
+      parameters that are all frozen or all non-frozen. For
+      ``use_orig_params=True``, FSDP supports mixing frozen and
+      non-frozen parameters, but it's recommended to avoid doing so to
+      prevent higher than expected gradient memory usage.
+
+    * As of PyTorch 1.12, FSDP offers limited support for shared
+      parameters. If enhanced shared parameter support is needed for
+      your use case, please post in
+      `this issue <https://github.com/pytorch/pytorch/issues/77724>`__.
+
+    * You should avoid modifying the parameters between forward and
+      backward without using the ``summon_full_params`` context, as
+      the modifications may not persist.
 
     Args:
         module (nn.Module):
@@ -1084,14 +1065,13 @@ 
Source code for torch.distributed.fsdp.fully_sharded_data_parallel
        """
         uninitialized = self._is_root is None
         self._assert_state(TrainingState.IDLE)
-        # Use `_unshard_params_recurse()` with `recurse=False` instead of
+        # Use `_unshard_params_for_summon()` with `recurse=False` instead of
         # `_unshard_fsdp_state_params()` directly to perform lazy
         # initialization, which is needed to initialize `FlatParameter`
         # parameter attributes as required by the unshard logic
-        with _unshard_params_recurse(
+        with _unshard_params_for_summon(
             self,
             self,
-            recurse=False,
             writeback=True,
             rank0_only=False,
             offload_to_cpu=False,
@@ -1099,9 +1079,9 @@ 
Source code for torch.distributed.fsdp.fully_sharded_data_parallel
):
             ret = super().apply(fn)
 
-        # Reset lazy init called in `_unshard_params_recurse()` since `apply()`
-        # may have been called on FSDP instance that is not truly a root, in
-        # which case it will be incorrectly marked as one.
+        # Reset lazy init called in `_unshard_params_for_summon()` since
+        # `apply()` may have been called on FSDP instance that is not truly a
+        # root, in which case it will be incorrectly marked as one.
         if uninitialized and self._is_root:
             for module in traversal_utils._get_fsdp_states(self):
                 module._reset_lazy_init()
@@ -1567,21 +1547,21 @@ 
Source code for torch.distributed.fsdp.fully_sharded_data_parallel
        Returns:
             Total norm of the parameters (viewed as a single vector).
 
-        .. note:: If every FSDP instance uses ``NO_SHARD``, meaning that no
-            gradients are sharded across ranks, then you may directly use
-            :func:`torch.nn.utils.clip_grad_norm_`.
+        If every FSDP instance uses ``NO_SHARD``, meaning that no
+        gradients are sharded across ranks, then you may directly use
+        :func:`torch.nn.utils.clip_grad_norm_`.
 
-        .. note:: If at least some FSDP instance uses a sharded strategy (i.e.
-            one other than ``NO_SHARD``), then you should use this method
-            instead of :func:`torch.nn.utils.clip_grad_norm_` since this method
-            handles the fact that gradients are sharded across ranks.
+        If at least some FSDP instance uses a sharded strategy (i.e.
+        one other than ``NO_SHARD``), then you should use this method
+        instead of :func:`torch.nn.utils.clip_grad_norm_` since this method
+        handles the fact that gradients are sharded across ranks.
 
-        .. note:: The total norm returned will have the "largest" dtype across
-            all parameters/gradients as defined by PyTorch's type promotion
-            semantics. For example, if *all* parameters/gradients use a low
-            precision dtype, then the returned norm's dtype will be that low
-            precision dtype, but if there exists at least one parameter/
-            gradient using FP32, then the returned norm's dtype will be FP32.
+        The total norm returned will have the "largest" dtype across
+        all parameters/gradients as defined by PyTorch's type promotion
+        semantics. For example, if *all* parameters/gradients use a low
+        precision dtype, then the returned norm's dtype will be that low
+        precision dtype, but if there exists at least one parameter/
+        gradient using FP32, then the returned norm's dtype will be FP32.
 
         .. warning:: This needs to be called on all ranks since it uses
             collective communications.
@@ -1845,19 +1825,19 @@ 
Source code for torch.distributed.fsdp.fully_sharded_data_parallel
        and ``"param_groups"``. The flattened parameters in ``FSDP`` modules
         contained in ``model`` are mapped back to their unflattened parameters.
 
-        .. warning:: This needs to be called on all ranks since it uses
-            collective communications. However, if ``rank0_only=True``, then
-            the state dict is only populated on rank 0, and all other ranks
-            return an empty :class:`dict`.
-
-        .. warning:: Unlike ``torch.optim.Optimizer.state_dict()``, this method
-            uses full parameter names as keys instead of parameter IDs.
-
-        .. note:: Like in :meth:`torch.optim.Optimizer.state_dict`, the tensors
-            contained in the optimizer state dict are not cloned, so there may
-            be aliasing surprises. For best practices, consider saving the
-            returned optimizer state dict immediately, e.g. using
-            ``torch.save()``.
+        This needs to be called on all ranks since it uses
+        collective communications. However, if ``rank0_only=True``, then
+        the state dict is only populated on rank 0, and all other ranks
+        return an empty :class:`dict`.
+
+        Unlike ``torch.optim.Optimizer.state_dict()``, this method
+        uses full parameter names as keys instead of parameter IDs.
+
+        Like in :meth:`torch.optim.Optimizer.state_dict`, the tensors
+        contained in the optimizer state dict are not cloned, so there may
+        be aliasing surprises. For best practices, consider saving the
+        returned optimizer state dict immediately, e.g. using
+        ``torch.save()``.
 
         Args:
             model (torch.nn.Module): Root module (which may or may not be a
diff --git a/docs/main/_modules/torch/distributed/nn/api/remote_module.html b/docs/main/_modules/torch/distributed/nn/api/remote_module.html
index b4c3c110ee04..8a8e23c0877e 100644
--- a/docs/main/_modules/torch/distributed/nn/api/remote_module.html
+++ b/docs/main/_modules/torch/distributed/nn/api/remote_module.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/optim/optimizer.html b/docs/main/_modules/torch/distributed/optim/optimizer.html
index c463eaba9136..ed4f8df85cd6 100644
--- a/docs/main/_modules/torch/distributed/optim/optimizer.html
+++ b/docs/main/_modules/torch/distributed/optim/optimizer.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/optim/post_localSGD_optimizer.html b/docs/main/_modules/torch/distributed/optim/post_localSGD_optimizer.html
index fe3221af1188..4dd2625f785d 100644
--- a/docs/main/_modules/torch/distributed/optim/post_localSGD_optimizer.html
+++ b/docs/main/_modules/torch/distributed/optim/post_localSGD_optimizer.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/optim/zero_redundancy_optimizer.html b/docs/main/_modules/torch/distributed/optim/zero_redundancy_optimizer.html
index b43cb7a9527d..019165a99ece 100644
--- a/docs/main/_modules/torch/distributed/optim/zero_redundancy_optimizer.html
+++ b/docs/main/_modules/torch/distributed/optim/zero_redundancy_optimizer.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/pipeline/sync/pipe.html b/docs/main/_modules/torch/distributed/pipeline/sync/pipe.html
index 396619b5f77c..28068153e535 100644
--- a/docs/main/_modules/torch/distributed/pipeline/sync/pipe.html
+++ b/docs/main/_modules/torch/distributed/pipeline/sync/pipe.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/pipeline/sync/skip/skippable.html b/docs/main/_modules/torch/distributed/pipeline/sync/skip/skippable.html
index 28ea6dd43008..06a12b6e356f 100644
--- a/docs/main/_modules/torch/distributed/pipeline/sync/skip/skippable.html
+++ b/docs/main/_modules/torch/distributed/pipeline/sync/skip/skippable.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/rpc.html b/docs/main/_modules/torch/distributed/rpc.html
index 1daa12ef1b3c..3176455ed84d 100644
--- a/docs/main/_modules/torch/distributed/rpc.html
+++ b/docs/main/_modules/torch/distributed/rpc.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/rpc/api.html b/docs/main/_modules/torch/distributed/rpc/api.html
index d93c4b97e219..20f7453be406 100644
--- a/docs/main/_modules/torch/distributed/rpc/api.html
+++ b/docs/main/_modules/torch/distributed/rpc/api.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/rpc/backend_registry.html b/docs/main/_modules/torch/distributed/rpc/backend_registry.html
index 694fe6435a32..0360d1b89a9e 100644
--- a/docs/main/_modules/torch/distributed/rpc/backend_registry.html
+++ b/docs/main/_modules/torch/distributed/rpc/backend_registry.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/rpc/functions.html b/docs/main/_modules/torch/distributed/rpc/functions.html
index 67fb3b93fa54..fddd8f8a1477 100644
--- a/docs/main/_modules/torch/distributed/rpc/functions.html
+++ b/docs/main/_modules/torch/distributed/rpc/functions.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/rpc/options.html b/docs/main/_modules/torch/distributed/rpc/options.html
index ea9d8a6f42e4..d3ef92227c14 100644
--- a/docs/main/_modules/torch/distributed/rpc/options.html
+++ b/docs/main/_modules/torch/distributed/rpc/options.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/tensor/parallel/api.html b/docs/main/_modules/torch/distributed/tensor/parallel/api.html
index 07ea4d86d43f..edd6cd03b0b0 100644
--- a/docs/main/_modules/torch/distributed/tensor/parallel/api.html
+++ b/docs/main/_modules/torch/distributed/tensor/parallel/api.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/tensor/parallel/loss.html b/docs/main/_modules/torch/distributed/tensor/parallel/loss.html
index ca1cd8cffa4d..0f0883700ca9 100644
--- a/docs/main/_modules/torch/distributed/tensor/parallel/loss.html
+++ b/docs/main/_modules/torch/distributed/tensor/parallel/loss.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributed/tensor/parallel/style.html b/docs/main/_modules/torch/distributed/tensor/parallel/style.html
index 038730835afc..5a66ae315f1e 100644
--- a/docs/main/_modules/torch/distributed/tensor/parallel/style.html
+++ b/docs/main/_modules/torch/distributed/tensor/parallel/style.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/bernoulli.html b/docs/main/_modules/torch/distributions/bernoulli.html
index ea6401fb257f..7a2227c4d98b 100644
--- a/docs/main/_modules/torch/distributions/bernoulli.html
+++ b/docs/main/_modules/torch/distributions/bernoulli.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/beta.html b/docs/main/_modules/torch/distributions/beta.html
index 8ba0f1a2a159..810f9daa5a25 100644
--- a/docs/main/_modules/torch/distributions/beta.html
+++ b/docs/main/_modules/torch/distributions/beta.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/binomial.html b/docs/main/_modules/torch/distributions/binomial.html
index eabd56fa1cba..300db67bb59e 100644
--- a/docs/main/_modules/torch/distributions/binomial.html
+++ b/docs/main/_modules/torch/distributions/binomial.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/categorical.html b/docs/main/_modules/torch/distributions/categorical.html
index ed24b5d6120f..978ddfcbae15 100644
--- a/docs/main/_modules/torch/distributions/categorical.html
+++ b/docs/main/_modules/torch/distributions/categorical.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/cauchy.html b/docs/main/_modules/torch/distributions/cauchy.html
index 4a2fe22aa0b6..0da7ccba0c85 100644
--- a/docs/main/_modules/torch/distributions/cauchy.html
+++ b/docs/main/_modules/torch/distributions/cauchy.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/chi2.html b/docs/main/_modules/torch/distributions/chi2.html
index e19704e0e3ed..468de76a2b2d 100644
--- a/docs/main/_modules/torch/distributions/chi2.html
+++ b/docs/main/_modules/torch/distributions/chi2.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/constraint_registry.html b/docs/main/_modules/torch/distributions/constraint_registry.html
index a341f8a6863c..b67399fad33b 100644
--- a/docs/main/_modules/torch/distributions/constraint_registry.html
+++ b/docs/main/_modules/torch/distributions/constraint_registry.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/constraints.html b/docs/main/_modules/torch/distributions/constraints.html
index 0acfcc6a7405..468e8b098455 100644
--- a/docs/main/_modules/torch/distributions/constraints.html
+++ b/docs/main/_modules/torch/distributions/constraints.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/continuous_bernoulli.html b/docs/main/_modules/torch/distributions/continuous_bernoulli.html
index ade4cebef05c..f67c8d50de26 100644
--- a/docs/main/_modules/torch/distributions/continuous_bernoulli.html
+++ b/docs/main/_modules/torch/distributions/continuous_bernoulli.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/dirichlet.html b/docs/main/_modules/torch/distributions/dirichlet.html
index 94ad55aaa59b..a41b94f959f8 100644
--- a/docs/main/_modules/torch/distributions/dirichlet.html
+++ b/docs/main/_modules/torch/distributions/dirichlet.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/distribution.html b/docs/main/_modules/torch/distributions/distribution.html
index 349b3bd65eee..e067a196f4bb 100644
--- a/docs/main/_modules/torch/distributions/distribution.html
+++ b/docs/main/_modules/torch/distributions/distribution.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/exp_family.html b/docs/main/_modules/torch/distributions/exp_family.html
index 79020f05b17d..09b4b33ec787 100644
--- a/docs/main/_modules/torch/distributions/exp_family.html
+++ b/docs/main/_modules/torch/distributions/exp_family.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/exponential.html b/docs/main/_modules/torch/distributions/exponential.html
index 6ba8d6d049c9..12efc3b5761e 100644
--- a/docs/main/_modules/torch/distributions/exponential.html
+++ b/docs/main/_modules/torch/distributions/exponential.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/fishersnedecor.html b/docs/main/_modules/torch/distributions/fishersnedecor.html
index 2cbda94b4a3b..798742781dce 100644
--- a/docs/main/_modules/torch/distributions/fishersnedecor.html
+++ b/docs/main/_modules/torch/distributions/fishersnedecor.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/gamma.html b/docs/main/_modules/torch/distributions/gamma.html
index da353894a63d..4a9cdd073268 100644
--- a/docs/main/_modules/torch/distributions/gamma.html
+++ b/docs/main/_modules/torch/distributions/gamma.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/geometric.html b/docs/main/_modules/torch/distributions/geometric.html
index e599b05eae6f..5c13747a31c7 100644
--- a/docs/main/_modules/torch/distributions/geometric.html
+++ b/docs/main/_modules/torch/distributions/geometric.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/gumbel.html b/docs/main/_modules/torch/distributions/gumbel.html
index 692e40ea13bf..8bfc898e4773 100644
--- a/docs/main/_modules/torch/distributions/gumbel.html
+++ b/docs/main/_modules/torch/distributions/gumbel.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/half_cauchy.html b/docs/main/_modules/torch/distributions/half_cauchy.html
index f2fb20a785ad..412a9426dd6d 100644
--- a/docs/main/_modules/torch/distributions/half_cauchy.html
+++ b/docs/main/_modules/torch/distributions/half_cauchy.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/half_normal.html b/docs/main/_modules/torch/distributions/half_normal.html
index d16a2e4e804c..fd8797b51cb1 100644
--- a/docs/main/_modules/torch/distributions/half_normal.html
+++ b/docs/main/_modules/torch/distributions/half_normal.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/independent.html b/docs/main/_modules/torch/distributions/independent.html
index 376bc091cdb3..c1c8a9a39b96 100644
--- a/docs/main/_modules/torch/distributions/independent.html
+++ b/docs/main/_modules/torch/distributions/independent.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/inverse_gamma.html b/docs/main/_modules/torch/distributions/inverse_gamma.html
index e81c3217c891..9e117a15447a 100644
--- a/docs/main/_modules/torch/distributions/inverse_gamma.html
+++ b/docs/main/_modules/torch/distributions/inverse_gamma.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/kl.html b/docs/main/_modules/torch/distributions/kl.html
index a59660ed5521..58712b44686e 100644
--- a/docs/main/_modules/torch/distributions/kl.html
+++ b/docs/main/_modules/torch/distributions/kl.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/kumaraswamy.html b/docs/main/_modules/torch/distributions/kumaraswamy.html
index ca5fff4f8a82..83b1ea15a74c 100644
--- a/docs/main/_modules/torch/distributions/kumaraswamy.html
+++ b/docs/main/_modules/torch/distributions/kumaraswamy.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/laplace.html b/docs/main/_modules/torch/distributions/laplace.html
index b271243e5fee..cdd22adae1a6 100644
--- a/docs/main/_modules/torch/distributions/laplace.html
+++ b/docs/main/_modules/torch/distributions/laplace.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/lkj_cholesky.html b/docs/main/_modules/torch/distributions/lkj_cholesky.html
index 0acd0810a829..28675e505c64 100644
--- a/docs/main/_modules/torch/distributions/lkj_cholesky.html
+++ b/docs/main/_modules/torch/distributions/lkj_cholesky.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/log_normal.html b/docs/main/_modules/torch/distributions/log_normal.html
index 682da002ef39..4f2044fa3476 100644
--- a/docs/main/_modules/torch/distributions/log_normal.html
+++ b/docs/main/_modules/torch/distributions/log_normal.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/lowrank_multivariate_normal.html b/docs/main/_modules/torch/distributions/lowrank_multivariate_normal.html
index 9c45861c3b19..1be2fc3dbdaa 100644
--- a/docs/main/_modules/torch/distributions/lowrank_multivariate_normal.html
+++ b/docs/main/_modules/torch/distributions/lowrank_multivariate_normal.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/mixture_same_family.html b/docs/main/_modules/torch/distributions/mixture_same_family.html
index abe8e904f2f1..360978c8174f 100644
--- a/docs/main/_modules/torch/distributions/mixture_same_family.html
+++ b/docs/main/_modules/torch/distributions/mixture_same_family.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/multinomial.html b/docs/main/_modules/torch/distributions/multinomial.html
index c36c4c28f6dd..c7001e67698a 100644
--- a/docs/main/_modules/torch/distributions/multinomial.html
+++ b/docs/main/_modules/torch/distributions/multinomial.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/multivariate_normal.html b/docs/main/_modules/torch/distributions/multivariate_normal.html
index f7af5a3f7b70..17757d279e55 100644
--- a/docs/main/_modules/torch/distributions/multivariate_normal.html
+++ b/docs/main/_modules/torch/distributions/multivariate_normal.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/negative_binomial.html b/docs/main/_modules/torch/distributions/negative_binomial.html
index 7b09134bc18c..53baa3acea56 100644
--- a/docs/main/_modules/torch/distributions/negative_binomial.html
+++ b/docs/main/_modules/torch/distributions/negative_binomial.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/normal.html b/docs/main/_modules/torch/distributions/normal.html
index 5f8f609f47a6..7c2721b541df 100644
--- a/docs/main/_modules/torch/distributions/normal.html
+++ b/docs/main/_modules/torch/distributions/normal.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/one_hot_categorical.html b/docs/main/_modules/torch/distributions/one_hot_categorical.html
index 5b99fc23068a..62794b4dd895 100644
--- a/docs/main/_modules/torch/distributions/one_hot_categorical.html
+++ b/docs/main/_modules/torch/distributions/one_hot_categorical.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/pareto.html b/docs/main/_modules/torch/distributions/pareto.html
index 178cf0d8c939..7f32f112dfb9 100644
--- a/docs/main/_modules/torch/distributions/pareto.html
+++ b/docs/main/_modules/torch/distributions/pareto.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/poisson.html b/docs/main/_modules/torch/distributions/poisson.html
index b99587f0cdef..7795881cc5f6 100644
--- a/docs/main/_modules/torch/distributions/poisson.html
+++ b/docs/main/_modules/torch/distributions/poisson.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/relaxed_bernoulli.html b/docs/main/_modules/torch/distributions/relaxed_bernoulli.html
index cc5b3755ee73..95299ee6ba08 100644
--- a/docs/main/_modules/torch/distributions/relaxed_bernoulli.html
+++ b/docs/main/_modules/torch/distributions/relaxed_bernoulli.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/relaxed_categorical.html b/docs/main/_modules/torch/distributions/relaxed_categorical.html
index f62681dc9f77..7d2d26ce5e20 100644
--- a/docs/main/_modules/torch/distributions/relaxed_categorical.html
+++ b/docs/main/_modules/torch/distributions/relaxed_categorical.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/studentT.html b/docs/main/_modules/torch/distributions/studentT.html
index 7cfad0ba9b5f..a0cd3e53af75 100644
--- a/docs/main/_modules/torch/distributions/studentT.html
+++ b/docs/main/_modules/torch/distributions/studentT.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/transformed_distribution.html b/docs/main/_modules/torch/distributions/transformed_distribution.html
index 638c1ddd64e4..7423bcb725c2 100644
--- a/docs/main/_modules/torch/distributions/transformed_distribution.html
+++ b/docs/main/_modules/torch/distributions/transformed_distribution.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/transforms.html b/docs/main/_modules/torch/distributions/transforms.html
index 7c7303b945a1..432046ff7abb 100644
--- a/docs/main/_modules/torch/distributions/transforms.html
+++ b/docs/main/_modules/torch/distributions/transforms.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/uniform.html b/docs/main/_modules/torch/distributions/uniform.html
index 1f8081513f2d..8879d501acae 100644
--- a/docs/main/_modules/torch/distributions/uniform.html
+++ b/docs/main/_modules/torch/distributions/uniform.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/utils.html b/docs/main/_modules/torch/distributions/utils.html
index ab6af42c1e1b..646de94a86cf 100644
--- a/docs/main/_modules/torch/distributions/utils.html
+++ b/docs/main/_modules/torch/distributions/utils.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/von_mises.html b/docs/main/_modules/torch/distributions/von_mises.html
index e721ad97ae27..58e8c2c72e54 100644
--- a/docs/main/_modules/torch/distributions/von_mises.html
+++ b/docs/main/_modules/torch/distributions/von_mises.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/weibull.html b/docs/main/_modules/torch/distributions/weibull.html
index 9fc6c249ac5d..da210da24f93 100644
--- a/docs/main/_modules/torch/distributions/weibull.html
+++ b/docs/main/_modules/torch/distributions/weibull.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/distributions/wishart.html b/docs/main/_modules/torch/distributions/wishart.html
index c9bc712d89ce..5ddbb4f7af30 100644
--- a/docs/main/_modules/torch/distributions/wishart.html
+++ b/docs/main/_modules/torch/distributions/wishart.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/export.html b/docs/main/_modules/torch/export.html
index 89b3e8f958bb..a632193450d0 100644
--- a/docs/main/_modules/torch/export.html
+++ b/docs/main/_modules/torch/export.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/export/dynamic_shapes.html b/docs/main/_modules/torch/export/dynamic_shapes.html
index 3f041f419ce8..525766d8864b 100644
--- a/docs/main/_modules/torch/export/dynamic_shapes.html
+++ b/docs/main/_modules/torch/export/dynamic_shapes.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/export/exported_program.html b/docs/main/_modules/torch/export/exported_program.html
index cdab2419281c..c263c973fca8 100644
--- a/docs/main/_modules/torch/export/exported_program.html
+++ b/docs/main/_modules/torch/export/exported_program.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
@@ -961,9 +961,15 @@ 
Source code for torch.export.exported_program
for name in buffers_to_remove:
             delattr(self.graph_module, name)
         # TODO(zhxhchen17) Return the new graph_signature directly.
-        gm, graph_signature = aot_export_module(
-            self.graph_module, fake_args, decompositions=decomp_table, trace_joint=False
-        )
+        from torch.export._trace import _ignore_backend_decomps
+
+        with _ignore_backend_decomps():
+            gm, graph_signature = aot_export_module(
+                self.graph_module,
+                fake_args,
+                decompositions=decomp_table,
+                trace_joint=False,
+            )
 
         # Update the signatures with the new placeholder names in case they
         # changed when calling aot_export
@@ -1059,7 +1065,12 @@ 
Source code for torch.export.exported_program
def _transform_do_not_use(self, *passes: PassType) -> "ExportedProgram":
         pm = PassManager(list(passes))
-        res = pm(self.graph_module)
+        # Since we abstractly run the passes, we need to disable backend decomp here
+        # again.
+        from torch.export._trace import _ignore_backend_decomps
+
+        with _ignore_backend_decomps():
+            res = pm(self.graph_module)
         transformed_gm = res.graph_module if res is not None else self.graph_module
         assert transformed_gm is not None
 
diff --git a/docs/main/_modules/torch/export/graph_signature.html b/docs/main/_modules/torch/export/graph_signature.html
index d3e942c9ee8d..08be88d80932 100644
--- a/docs/main/_modules/torch/export/graph_signature.html
+++ b/docs/main/_modules/torch/export/graph_signature.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/export/unflatten.html b/docs/main/_modules/torch/export/unflatten.html
index 8f982ecad85c..4e568f6f3b04 100644
--- a/docs/main/_modules/torch/export/unflatten.html
+++ b/docs/main/_modules/torch/export/unflatten.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/func.html b/docs/main/_modules/torch/func.html
index 70fbba57aec0..9dcf28489ee1 100644
--- a/docs/main/_modules/torch/func.html
+++ b/docs/main/_modules/torch/func.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/functional.html b/docs/main/_modules/torch/functional.html
index 936bad2ab416..afce638fe5ae 100644
--- a/docs/main/_modules/torch/functional.html
+++ b/docs/main/_modules/torch/functional.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/futures.html b/docs/main/_modules/torch/futures.html
index 90651954498b..0c139af0bd0b 100644
--- a/docs/main/_modules/torch/futures.html
+++ b/docs/main/_modules/torch/futures.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/fx/_symbolic_trace.html b/docs/main/_modules/torch/fx/_symbolic_trace.html
index 5332bd7e9c1c..bb61d4409f92 100644
--- a/docs/main/_modules/torch/fx/_symbolic_trace.html
+++ b/docs/main/_modules/torch/fx/_symbolic_trace.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/fx/experimental/symbolic_shapes.html b/docs/main/_modules/torch/fx/experimental/symbolic_shapes.html
index 088d1e657ffa..db68255cc0c5 100644
--- a/docs/main/_modules/torch/fx/experimental/symbolic_shapes.html
+++ b/docs/main/_modules/torch/fx/experimental/symbolic_shapes.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/fx/graph.html b/docs/main/_modules/torch/fx/graph.html
index 50f80e114754..d47fcd4cf372 100644
--- a/docs/main/_modules/torch/fx/graph.html
+++ b/docs/main/_modules/torch/fx/graph.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/fx/graph_module.html b/docs/main/_modules/torch/fx/graph_module.html
index be36b19be6d7..7a94f039c90c 100644
--- a/docs/main/_modules/torch/fx/graph_module.html
+++ b/docs/main/_modules/torch/fx/graph_module.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/fx/interpreter.html b/docs/main/_modules/torch/fx/interpreter.html
index b79814a7ecab..f802db107350 100644
--- a/docs/main/_modules/torch/fx/interpreter.html
+++ b/docs/main/_modules/torch/fx/interpreter.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/fx/node.html b/docs/main/_modules/torch/fx/node.html
index f6f8372fdc28..9942b2a0a965 100644
--- a/docs/main/_modules/torch/fx/node.html
+++ b/docs/main/_modules/torch/fx/node.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/fx/proxy.html b/docs/main/_modules/torch/fx/proxy.html
index ecd75d96e14b..a3dccd1d053a 100644
--- a/docs/main/_modules/torch/fx/proxy.html
+++ b/docs/main/_modules/torch/fx/proxy.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/fx/subgraph_rewriter.html b/docs/main/_modules/torch/fx/subgraph_rewriter.html
index 5358495befc8..8aa403048291 100644
--- a/docs/main/_modules/torch/fx/subgraph_rewriter.html
+++ b/docs/main/_modules/torch/fx/subgraph_rewriter.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/hub.html b/docs/main/_modules/torch/hub.html
index 374896a0522a..54456a6a7479 100644
--- a/docs/main/_modules/torch/hub.html
+++ b/docs/main/_modules/torch/hub.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/jit.html b/docs/main/_modules/torch/jit.html
index 0879d4d60c96..612f11bc45d8 100644
--- a/docs/main/_modules/torch/jit.html
+++ b/docs/main/_modules/torch/jit.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/jit/_async.html b/docs/main/_modules/torch/jit/_async.html
index bc818fc37d52..e8733f335869 100644
--- a/docs/main/_modules/torch/jit/_async.html
+++ b/docs/main/_modules/torch/jit/_async.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/jit/_freeze.html b/docs/main/_modules/torch/jit/_freeze.html
index 0a9739a0b8f6..77e2ffb73ef3 100644
--- a/docs/main/_modules/torch/jit/_freeze.html
+++ b/docs/main/_modules/torch/jit/_freeze.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/jit/_fuser.html b/docs/main/_modules/torch/jit/_fuser.html
index 2fb17b94830e..99d6560af858 100644
--- a/docs/main/_modules/torch/jit/_fuser.html
+++ b/docs/main/_modules/torch/jit/_fuser.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/jit/_script.html b/docs/main/_modules/torch/jit/_script.html
index 7566d89c99a1..faab27ebd13f 100644
--- a/docs/main/_modules/torch/jit/_script.html
+++ b/docs/main/_modules/torch/jit/_script.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/jit/_serialization.html b/docs/main/_modules/torch/jit/_serialization.html
index c4d91ef302a2..0d8e1195af4f 100644
--- a/docs/main/_modules/torch/jit/_serialization.html
+++ b/docs/main/_modules/torch/jit/_serialization.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/jit/_trace.html b/docs/main/_modules/torch/jit/_trace.html
index 3ed3d410ebd8..fb009b50188f 100644
--- a/docs/main/_modules/torch/jit/_trace.html
+++ b/docs/main/_modules/torch/jit/_trace.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/library.html b/docs/main/_modules/torch/library.html
index b8087d36a830..8d842c76ba80 100644
--- a/docs/main/_modules/torch/library.html
+++ b/docs/main/_modules/torch/library.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
@@ -490,6 +490,8 @@ 
Source code for torch.library
 import re
 import contextlib
 import sys
+from torch._library.custom_ops import custom_op
+
 
 __all__ = [
     'Library',
@@ -498,6 +500,7 @@ 
Source code for torch.library
     'fallthrough_kernel',
     'impl_abstract',
     'get_ctx',
+    'custom_op',
 ]
 
 # Set containing the combination of (namespace, operator, DispatchKey) for which a new kernel has been registered
@@ -575,8 +578,7 @@ 
Source code for torch.library
             name of the operator as inferred from the schema.
 
         Example::
-            >>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_LIBRARY)
-            >>> my_lib = Library("foo", "DEF")
+            >>> my_lib = Library("mylib", "DEF")
             >>> my_lib.define("sum(Tensor self) -> Tensor")
         '''
         # This is added because we also want to disallow PURE_FUNCTION alias analysis which is a valid
@@ -660,6 +662,8 @@ 
Source code for torch.library
         for handle in self._registration_handles:
             handle.destroy()
         self._registration_handles.clear()
+        global _impls
+        _impls -= self._op_impls
         for name in self._op_defs:
             # Delete the cached torch.ops.ns.foo if it was registered.
             # Otherwise, accessing it leads to a segfault.
@@ -731,7 +735,6 @@ 
Source code for torch.library
             torch.Tag carefully before applying it.
 
     Example::
-        >>> # xdoctest: +REQUIRES(env:TORCH_DOCTEST_LIBRARY)
         >>> import torch
         >>> import numpy as np
         >>>
@@ -739,14 +742,14 @@ 
Source code for torch.library
         >>> torch.library.define("mylib::sin", "(Tensor x) -> Tensor")
         >>>
         >>> # Add implementations for the operator
-        >>> @torch.library.impl("mylibrary::sin", "cpu")
+        >>> @torch.library.impl("mylib::sin", "cpu")
         >>> def f(x):
         >>>     return torch.from_numpy(np.sin(x.numpy()))
         >>>
         >>> # Call the new operator from torch.ops.
         >>> x = torch.randn(3)
         >>> y = torch.ops.mylib.sin(x)
-        >>> assert torch.allclose(y, x)
+        >>> assert torch.allclose(y, x.sin())
 
     """
     if not isinstance(qualname, str):
@@ -799,15 +802,15 @@ 
Source code for torch.library
         >>> import numpy as np
         >>>
         >>> # Define the operator
-        >>> torch.library.define("mylibrary::sin", "(Tensor x) -> Tensor")
+        >>> torch.library.define("mylib::mysin", "(Tensor x) -> Tensor")
         >>>
         >>> # Add implementations for the cpu device
-        >>> @torch.library.impl("mylibrary::sin", "cpu")
+        >>> @torch.library.impl("mylib::mysin", "cpu")
         >>> def f(x):
         >>>     return torch.from_numpy(np.sin(x.numpy()))
         >>>
         >>> x = torch.randn(3)
-        >>> y = torch.ops.mylibrary.sin(x)
+        >>> y = torch.ops.mylib.mysin(x)
         >>> assert torch.allclose(y, x.sin())
     """
     if isinstance(types, str):
@@ -895,7 +898,7 @@ 
Source code for torch.library
         >>>     "(Tensor x, Tensor weight, Tensor bias) -> Tensor")
         >>>
         >>> @torch.library.impl_abstract("mylib::custom_linear")
-        >>> def custom_linear_abstract(x, weight):
+        >>> def custom_linear_abstract(x, weight, bias):
         >>>     assert x.dim() == 2
         >>>     assert weight.dim() == 2
         >>>     assert bias.dim() == 1
@@ -905,6 +908,14 @@ 
Source code for torch.library
         >>>
         >>>     return (x @ weight.t()) + bias
         >>>
+        >>> with torch._subclasses.fake_tensor.FakeTensorMode():
+        >>>     x = torch.randn(2, 3)
+        >>>     w = torch.randn(3, 3)
+        >>>     b = torch.randn(3)
+        >>>     y = torch.ops.mylib.custom_linear(x, w, b)
+        >>>
+        >>> assert y.shape == (2, 3)
+        >>>
         >>> # Example 2: an operator with data-dependent output shape
         >>> torch.library.define("mylib::custom_nonzero", "(Tensor x) -> Tensor")
         >>>
@@ -925,6 +936,14 @@ 
Source code for torch.library
         >>>     x_np = x.numpy()
         >>>     res = np.stack(np.nonzero(x_np), axis=1)
         >>>     return torch.tensor(res, device=x.device)
+        >>>
+        >>> from torch.fx.experimental.proxy_tensor import make_fx
+        >>>
+        >>> x = torch.tensor([0, 1, 2, 3, 4, 0])
+        >>> trace = make_fx(torch.ops.mylib.custom_nonzero, tracing_mode="symbolic")(x)
+        >>> trace.print_readable()
+        >>>
+        >>> assert torch.allclose(trace(x), torch.ops.mylib.custom_nonzero(x))
 
     """
     source = torch._library.utils.get_source(_stacklevel + 1)
diff --git a/docs/main/_modules/torch/monitor.html b/docs/main/_modules/torch/monitor.html
index 4d9922d5bff7..c045d47ff9c6 100644
--- a/docs/main/_modules/torch/monitor.html
+++ b/docs/main/_modules/torch/monitor.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/mps.html b/docs/main/_modules/torch/mps.html
index 2c7332bb9936..c19c8f57ca80 100644
--- a/docs/main/_modules/torch/mps.html
+++ b/docs/main/_modules/torch/mps.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/mps/event.html b/docs/main/_modules/torch/mps/event.html
index 9f08dc98fb5c..30f5f4159dcc 100644
--- a/docs/main/_modules/torch/mps/event.html
+++ b/docs/main/_modules/torch/mps/event.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/mps/profiler.html b/docs/main/_modules/torch/mps/profiler.html
index f759abbade70..9cafa0005b1b 100644
--- a/docs/main/_modules/torch/mps/profiler.html
+++ b/docs/main/_modules/torch/mps/profiler.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/multiprocessing.html b/docs/main/_modules/torch/multiprocessing.html
index bc52275d3cf8..509c0e0d1b5f 100644
--- a/docs/main/_modules/torch/multiprocessing.html
+++ b/docs/main/_modules/torch/multiprocessing.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/multiprocessing/spawn.html b/docs/main/_modules/torch/multiprocessing/spawn.html
index e71bcf69b9c3..d09edb1c3494 100644
--- a/docs/main/_modules/torch/multiprocessing/spawn.html
+++ b/docs/main/_modules/torch/multiprocessing/spawn.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nested.html b/docs/main/_modules/torch/nested.html
index 39670b3da63e..495fda0297ba 100644
--- a/docs/main/_modules/torch/nested.html
+++ b/docs/main/_modules/torch/nested.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/attention.html b/docs/main/_modules/torch/nn/attention.html
index 793e20ac1491..e6f4b4a665c1 100644
--- a/docs/main/_modules/torch/nn/attention.html
+++ b/docs/main/_modules/torch/nn/attention.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/attention/bias.html b/docs/main/_modules/torch/nn/attention/bias.html
index 322125cc994f..e1ccd0ded721 100644
--- a/docs/main/_modules/torch/nn/attention/bias.html
+++ b/docs/main/_modules/torch/nn/attention/bias.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/functional.html b/docs/main/_modules/torch/nn/functional.html
index b954fea51b3e..910e7321f79e 100644
--- a/docs/main/_modules/torch/nn/functional.html
+++ b/docs/main/_modules/torch/nn/functional.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/init.html b/docs/main/_modules/torch/nn/init.html
index 4a63a1d81f28..1cf4e6c4aab2 100644
--- a/docs/main/_modules/torch/nn/init.html
+++ b/docs/main/_modules/torch/nn/init.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/activation.html b/docs/main/_modules/torch/nn/modules/activation.html
index 19c222e3746e..89e5d96da6b7 100644
--- a/docs/main/_modules/torch/nn/modules/activation.html
+++ b/docs/main/_modules/torch/nn/modules/activation.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/adaptive.html b/docs/main/_modules/torch/nn/modules/adaptive.html
index 8906d8cb2c2b..ed2c47eb1296 100644
--- a/docs/main/_modules/torch/nn/modules/adaptive.html
+++ b/docs/main/_modules/torch/nn/modules/adaptive.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/batchnorm.html b/docs/main/_modules/torch/nn/modules/batchnorm.html
index c80f43f12fe8..45baeb2e6ff4 100644
--- a/docs/main/_modules/torch/nn/modules/batchnorm.html
+++ b/docs/main/_modules/torch/nn/modules/batchnorm.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/channelshuffle.html b/docs/main/_modules/torch/nn/modules/channelshuffle.html
index 0e2f81a2d80c..3929bd187457 100644
--- a/docs/main/_modules/torch/nn/modules/channelshuffle.html
+++ b/docs/main/_modules/torch/nn/modules/channelshuffle.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/container.html b/docs/main/_modules/torch/nn/modules/container.html
index 7ed55bad7c88..c0b76ea6a3ec 100644
--- a/docs/main/_modules/torch/nn/modules/container.html
+++ b/docs/main/_modules/torch/nn/modules/container.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/conv.html b/docs/main/_modules/torch/nn/modules/conv.html
index 5ad712de929a..163e53aaca66 100644
--- a/docs/main/_modules/torch/nn/modules/conv.html
+++ b/docs/main/_modules/torch/nn/modules/conv.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/distance.html b/docs/main/_modules/torch/nn/modules/distance.html
index 5c5211916fb7..4903c81a8bbe 100644
--- a/docs/main/_modules/torch/nn/modules/distance.html
+++ b/docs/main/_modules/torch/nn/modules/distance.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/dropout.html b/docs/main/_modules/torch/nn/modules/dropout.html
index c10ea3e87356..2e76d29cc4f7 100644
--- a/docs/main/_modules/torch/nn/modules/dropout.html
+++ b/docs/main/_modules/torch/nn/modules/dropout.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/flatten.html b/docs/main/_modules/torch/nn/modules/flatten.html
index 5e73fa03e142..1a50b80e12aa 100644
--- a/docs/main/_modules/torch/nn/modules/flatten.html
+++ b/docs/main/_modules/torch/nn/modules/flatten.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/fold.html b/docs/main/_modules/torch/nn/modules/fold.html
index 58dee0419663..159812527cb0 100644
--- a/docs/main/_modules/torch/nn/modules/fold.html
+++ b/docs/main/_modules/torch/nn/modules/fold.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/instancenorm.html b/docs/main/_modules/torch/nn/modules/instancenorm.html
index d8b90873d025..2035c84da366 100644
--- a/docs/main/_modules/torch/nn/modules/instancenorm.html
+++ b/docs/main/_modules/torch/nn/modules/instancenorm.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/lazy.html b/docs/main/_modules/torch/nn/modules/lazy.html
index 73cffd7cba90..7a78a5f2d1cd 100644
--- a/docs/main/_modules/torch/nn/modules/lazy.html
+++ b/docs/main/_modules/torch/nn/modules/lazy.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/linear.html b/docs/main/_modules/torch/nn/modules/linear.html
index e3671927936e..0be083ca5d6f 100644
--- a/docs/main/_modules/torch/nn/modules/linear.html
+++ b/docs/main/_modules/torch/nn/modules/linear.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/loss.html b/docs/main/_modules/torch/nn/modules/loss.html
index e692961ad9e8..cfd94421ce16 100644
--- a/docs/main/_modules/torch/nn/modules/loss.html
+++ b/docs/main/_modules/torch/nn/modules/loss.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/module.html b/docs/main/_modules/torch/nn/modules/module.html
index 126444f60d03..c118c3a830df 100644
--- a/docs/main/_modules/torch/nn/modules/module.html
+++ b/docs/main/_modules/torch/nn/modules/module.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/normalization.html b/docs/main/_modules/torch/nn/modules/normalization.html
index 2e60017b8da7..8068ff2967bf 100644
--- a/docs/main/_modules/torch/nn/modules/normalization.html
+++ b/docs/main/_modules/torch/nn/modules/normalization.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/padding.html b/docs/main/_modules/torch/nn/modules/padding.html
index d75615027ac2..7dfa03e6ea1f 100644
--- a/docs/main/_modules/torch/nn/modules/padding.html
+++ b/docs/main/_modules/torch/nn/modules/padding.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/pixelshuffle.html b/docs/main/_modules/torch/nn/modules/pixelshuffle.html
index c4ef5e634721..184e0ae5271a 100644
--- a/docs/main/_modules/torch/nn/modules/pixelshuffle.html
+++ b/docs/main/_modules/torch/nn/modules/pixelshuffle.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/pooling.html b/docs/main/_modules/torch/nn/modules/pooling.html
index c4db854b4f0f..ff2002f2590d 100644
--- a/docs/main/_modules/torch/nn/modules/pooling.html
+++ b/docs/main/_modules/torch/nn/modules/pooling.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/rnn.html b/docs/main/_modules/torch/nn/modules/rnn.html
index b8de41526390..6712652d99e3 100644
--- a/docs/main/_modules/torch/nn/modules/rnn.html
+++ b/docs/main/_modules/torch/nn/modules/rnn.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/sparse.html b/docs/main/_modules/torch/nn/modules/sparse.html
index 010f8d35a49d..6edafe753920 100644
--- a/docs/main/_modules/torch/nn/modules/sparse.html
+++ b/docs/main/_modules/torch/nn/modules/sparse.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/transformer.html b/docs/main/_modules/torch/nn/modules/transformer.html
index d27a16dbe28a..125c87901c01 100644
--- a/docs/main/_modules/torch/nn/modules/transformer.html
+++ b/docs/main/_modules/torch/nn/modules/transformer.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/modules/upsampling.html b/docs/main/_modules/torch/nn/modules/upsampling.html
index 467a0d69d65d..ebf7fecc3e75 100644
--- a/docs/main/_modules/torch/nn/modules/upsampling.html
+++ b/docs/main/_modules/torch/nn/modules/upsampling.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/parallel/comm.html b/docs/main/_modules/torch/nn/parallel/comm.html
index 390d0ce25601..7c17366a1b9a 100644
--- a/docs/main/_modules/torch/nn/parallel/comm.html
+++ b/docs/main/_modules/torch/nn/parallel/comm.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/parallel/data_parallel.html b/docs/main/_modules/torch/nn/parallel/data_parallel.html
index e00a17fa73ef..9a4dcbee8157 100644
--- a/docs/main/_modules/torch/nn/parallel/data_parallel.html
+++ b/docs/main/_modules/torch/nn/parallel/data_parallel.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/parallel/distributed.html b/docs/main/_modules/torch/nn/parallel/distributed.html
index c4694ff22b39..024f2e3a0b30 100644
--- a/docs/main/_modules/torch/nn/parallel/distributed.html
+++ b/docs/main/_modules/torch/nn/parallel/distributed.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/parameter.html b/docs/main/_modules/torch/nn/parameter.html
index a380c3ed1d12..060a18842a92 100644
--- a/docs/main/_modules/torch/nn/parameter.html
+++ b/docs/main/_modules/torch/nn/parameter.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/utils/clip_grad.html b/docs/main/_modules/torch/nn/utils/clip_grad.html
index 3e27fd162e83..93f0734daae5 100644
--- a/docs/main/_modules/torch/nn/utils/clip_grad.html
+++ b/docs/main/_modules/torch/nn/utils/clip_grad.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/utils/convert_parameters.html b/docs/main/_modules/torch/nn/utils/convert_parameters.html
index 8b43c98632c9..03480452f8c7 100644
--- a/docs/main/_modules/torch/nn/utils/convert_parameters.html
+++ b/docs/main/_modules/torch/nn/utils/convert_parameters.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/utils/fusion.html b/docs/main/_modules/torch/nn/utils/fusion.html
index d34e85d261a5..c3db67f5430f 100644
--- a/docs/main/_modules/torch/nn/utils/fusion.html
+++ b/docs/main/_modules/torch/nn/utils/fusion.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/utils/init.html b/docs/main/_modules/torch/nn/utils/init.html
index 86f277b6c838..ecb51c86966f 100644
--- a/docs/main/_modules/torch/nn/utils/init.html
+++ b/docs/main/_modules/torch/nn/utils/init.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/utils/memory_format.html b/docs/main/_modules/torch/nn/utils/memory_format.html
index 87da2971e49a..9fab20d4cd02 100644
--- a/docs/main/_modules/torch/nn/utils/memory_format.html
+++ b/docs/main/_modules/torch/nn/utils/memory_format.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/utils/parametrizations.html b/docs/main/_modules/torch/nn/utils/parametrizations.html
index 00032357836d..acff9a667bfe 100644
--- a/docs/main/_modules/torch/nn/utils/parametrizations.html
+++ b/docs/main/_modules/torch/nn/utils/parametrizations.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/utils/parametrize.html b/docs/main/_modules/torch/nn/utils/parametrize.html
index 2856bfe6f2b0..25ac29d392df 100644
--- a/docs/main/_modules/torch/nn/utils/parametrize.html
+++ b/docs/main/_modules/torch/nn/utils/parametrize.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/utils/prune.html b/docs/main/_modules/torch/nn/utils/prune.html
index 9d6022a83338..92588c3e47cf 100644
--- a/docs/main/_modules/torch/nn/utils/prune.html
+++ b/docs/main/_modules/torch/nn/utils/prune.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/utils/rnn.html b/docs/main/_modules/torch/nn/utils/rnn.html
index 1a85c53aed7c..6d23d5ac6d44 100644
--- a/docs/main/_modules/torch/nn/utils/rnn.html
+++ b/docs/main/_modules/torch/nn/utils/rnn.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
@@ -829,9 +829,9 @@ 
Source code for torch.nn.utils.rnn
     r"""Pad a list of variable length Tensors with ``padding_value``.
 
     ``pad_sequence`` stacks a list of Tensors along a new dimension,
-    and pads them to equal length. For example, if the input is a list of
-    sequences with size ``L x *`` and ``batch_first`` is False, the output is
-    of size ``T x B x *``.
+    and pads them to equal length. For example, consider a list of sequences
+    with size ``L x *`` as the input. If ``batch_first`` is ``False``,
+    the output is of size ``T x B x *``, and ``B x T x *`` otherwise.
 
     `B` is batch size. It is equal to the number of elements in ``sequences``.
     `T` is length of the longest sequence.
diff --git a/docs/main/_modules/torch/nn/utils/spectral_norm.html b/docs/main/_modules/torch/nn/utils/spectral_norm.html
index d4e3f508a2a3..55dd16e2a162 100644
--- a/docs/main/_modules/torch/nn/utils/spectral_norm.html
+++ b/docs/main/_modules/torch/nn/utils/spectral_norm.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/utils/stateless.html b/docs/main/_modules/torch/nn/utils/stateless.html
index a62bc40e5868..cd21b49a9f8c 100644
--- a/docs/main/_modules/torch/nn/utils/stateless.html
+++ b/docs/main/_modules/torch/nn/utils/stateless.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/nn/utils/weight_norm.html b/docs/main/_modules/torch/nn/utils/weight_norm.html
index b4ed64b1a4cc..c1ff6faacb5e 100644
--- a/docs/main/_modules/torch/nn/utils/weight_norm.html
+++ b/docs/main/_modules/torch/nn/utils/weight_norm.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/onnx.html b/docs/main/_modules/torch/onnx.html
index be847280746f..bdd96d352d1a 100644
--- a/docs/main/_modules/torch/onnx.html
+++ b/docs/main/_modules/torch/onnx.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/onnx/_internal/exporter.html b/docs/main/_modules/torch/onnx/_internal/exporter.html
index 54ca6ae11b76..28a1ff7b8c31 100644
--- a/docs/main/_modules/torch/onnx/_internal/exporter.html
+++ b/docs/main/_modules/torch/onnx/_internal/exporter.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/onnx/_type_utils.html b/docs/main/_modules/torch/onnx/_type_utils.html
index 7922759be880..54012638a586 100644
--- a/docs/main/_modules/torch/onnx/_type_utils.html
+++ b/docs/main/_modules/torch/onnx/_type_utils.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/onnx/utils.html b/docs/main/_modules/torch/onnx/utils.html
index 52943b805ba7..1dc78fceccce 100644
--- a/docs/main/_modules/torch/onnx/utils.html
+++ b/docs/main/_modules/torch/onnx/utils.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/onnx/verification.html b/docs/main/_modules/torch/onnx/verification.html
index fcc710faf0d5..4cd2fe542c1a 100644
--- a/docs/main/_modules/torch/onnx/verification.html
+++ b/docs/main/_modules/torch/onnx/verification.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/adadelta.html b/docs/main/_modules/torch/optim/adadelta.html
index ebab9b8746ab..5bdc01e84519 100644
--- a/docs/main/_modules/torch/optim/adadelta.html
+++ b/docs/main/_modules/torch/optim/adadelta.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/adagrad.html b/docs/main/_modules/torch/optim/adagrad.html
index 2a62a9d71768..3f28e31aacd7 100644
--- a/docs/main/_modules/torch/optim/adagrad.html
+++ b/docs/main/_modules/torch/optim/adagrad.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/adam.html b/docs/main/_modules/torch/optim/adam.html
index 51d415b078f8..03087061a502 100644
--- a/docs/main/_modules/torch/optim/adam.html
+++ b/docs/main/_modules/torch/optim/adam.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/adamax.html b/docs/main/_modules/torch/optim/adamax.html
index 58d40b57eb59..ff931421e440 100644
--- a/docs/main/_modules/torch/optim/adamax.html
+++ b/docs/main/_modules/torch/optim/adamax.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/adamw.html b/docs/main/_modules/torch/optim/adamw.html
index d1a7c38ff9c8..25c79c62b8b4 100644
--- a/docs/main/_modules/torch/optim/adamw.html
+++ b/docs/main/_modules/torch/optim/adamw.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/asgd.html b/docs/main/_modules/torch/optim/asgd.html
index 2a3cc1b5b27c..a9e14e4db6c6 100644
--- a/docs/main/_modules/torch/optim/asgd.html
+++ b/docs/main/_modules/torch/optim/asgd.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/lbfgs.html b/docs/main/_modules/torch/optim/lbfgs.html
index 4f773d9479c4..0163f7528657 100644
--- a/docs/main/_modules/torch/optim/lbfgs.html
+++ b/docs/main/_modules/torch/optim/lbfgs.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/lr_scheduler.html b/docs/main/_modules/torch/optim/lr_scheduler.html
index a6cf5aa70f62..837391c79363 100644
--- a/docs/main/_modules/torch/optim/lr_scheduler.html
+++ b/docs/main/_modules/torch/optim/lr_scheduler.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/nadam.html b/docs/main/_modules/torch/optim/nadam.html
index 3c3fbc80dc37..ddff2ce7e933 100644
--- a/docs/main/_modules/torch/optim/nadam.html
+++ b/docs/main/_modules/torch/optim/nadam.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/optimizer.html b/docs/main/_modules/torch/optim/optimizer.html
index 30a17fb38413..2570597ee1a8 100644
--- a/docs/main/_modules/torch/optim/optimizer.html
+++ b/docs/main/_modules/torch/optim/optimizer.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/radam.html b/docs/main/_modules/torch/optim/radam.html
index a84f01b1866a..7414366098e4 100644
--- a/docs/main/_modules/torch/optim/radam.html
+++ b/docs/main/_modules/torch/optim/radam.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/rmsprop.html b/docs/main/_modules/torch/optim/rmsprop.html
index 6309773045cf..c2b5f9d4c40e 100644
--- a/docs/main/_modules/torch/optim/rmsprop.html
+++ b/docs/main/_modules/torch/optim/rmsprop.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/rprop.html b/docs/main/_modules/torch/optim/rprop.html
index 53fb8fd3ba81..d20012ca7564 100644
--- a/docs/main/_modules/torch/optim/rprop.html
+++ b/docs/main/_modules/torch/optim/rprop.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/optim/sgd.html b/docs/main/_modules/torch/optim/sgd.html
index 6edf1c0c2a17..03515b69d298 100644
--- a/docs/main/_modules/torch/optim/sgd.html
+++ b/docs/main/_modules/torch/optim/sgd.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
@@ -535,7 +535,8 @@ 
Source code for torch.optim.sgd
                     has_sparse_grad = True
 
                 state = self.state[p]
-                momentum_buffer_list.append(state.get('momentum_buffer'))
+                if group["momentum"] != 0:
+                    momentum_buffer_list.append(state.get('momentum_buffer'))
 
         return has_sparse_grad
 
@@ -574,10 +575,11 @@ 
Source code for torch.optim.sgd
                 grad_scale=getattr(self, "grad_scale", None),
                 found_inf=getattr(self, "found_inf", None))
 
-            # update momentum_buffers in state
-            for p, momentum_buffer in zip(params_with_grad, momentum_buffer_list):
-                state = self.state[p]
-                state['momentum_buffer'] = momentum_buffer
+            if group["momentum"] != 0:
+                # update momentum_buffers in state
+                for p, momentum_buffer in zip(params_with_grad, momentum_buffer_list):
+                    state = self.state[p]
+                    state['momentum_buffer'] = momentum_buffer
 
         return loss

 
diff --git a/docs/main/_modules/torch/optim/sparse_adam.html b/docs/main/_modules/torch/optim/sparse_adam.html
index bffbdff5f174..dd0fa4956794 100644
--- a/docs/main/_modules/torch/optim/sparse_adam.html
+++ b/docs/main/_modules/torch/optim/sparse_adam.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/overrides.html b/docs/main/_modules/torch/overrides.html
index 0bb333742dc5..63a8dd1634d9 100644
--- a/docs/main/_modules/torch/overrides.html
+++ b/docs/main/_modules/torch/overrides.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/package/file_structure_representation.html b/docs/main/_modules/torch/package/file_structure_representation.html
index 81e886bcfe00..52b72e5d95a7 100644
--- a/docs/main/_modules/torch/package/file_structure_representation.html
+++ b/docs/main/_modules/torch/package/file_structure_representation.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/package/package_exporter.html b/docs/main/_modules/torch/package/package_exporter.html
index 15698a8b100a..987555edb5ad 100644
--- a/docs/main/_modules/torch/package/package_exporter.html
+++ b/docs/main/_modules/torch/package/package_exporter.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/package/package_importer.html b/docs/main/_modules/torch/package/package_importer.html
index a0da25ae9266..98fa606218f5 100644
--- a/docs/main/_modules/torch/package/package_importer.html
+++ b/docs/main/_modules/torch/package/package_importer.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/profiler/itt.html b/docs/main/_modules/torch/profiler/itt.html
index 2838f390dd47..3fbc87535561 100644
--- a/docs/main/_modules/torch/profiler/itt.html
+++ b/docs/main/_modules/torch/profiler/itt.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/profiler/profiler.html b/docs/main/_modules/torch/profiler/profiler.html
index aaaedcdc7dc0..2202c27d88b2 100644
--- a/docs/main/_modules/torch/profiler/profiler.html
+++ b/docs/main/_modules/torch/profiler/profiler.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
@@ -698,18 +698,11 @@ 
Source code for torch.profiler.profiler
             return self.profiler.export_chrome_trace(path)

 
 
[docs]    def export_stacks(self, path: str, metric: str = "self_cpu_time_total"):
-        """Save stack traces in a file in a format suitable for visualization.
+        """Save stack traces to a file
 
         Args:
             path (str): save stacks file to this location;
             metric (str): metric to use: "self_cpu_time_total" or "self_cuda_time_total"
-
-        .. note::
-            Example of using FlameGraph tool:
-
-            - git clone https://github.com/brendangregg/FlameGraph
-            - cd FlameGraph
-            - ./flamegraph.pl --title "CPU time" --countname "us." profiler.stacks > perf_viz.svg
         """
         assert self.profiler
         return self.profiler.export_stacks(path, metric)

diff --git a/docs/main/_modules/torch/quasirandom.html b/docs/main/_modules/torch/quasirandom.html
index 8b7dca22a081..0aa76ba0b9dd 100644
--- a/docs/main/_modules/torch/quasirandom.html
+++ b/docs/main/_modules/torch/quasirandom.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/random.html b/docs/main/_modules/torch/random.html
index 18aac44f38b3..940321853da4 100644
--- a/docs/main/_modules/torch/random.html
+++ b/docs/main/_modules/torch/random.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/serialization.html b/docs/main/_modules/torch/serialization.html
index 69d68b7c1c9a..9a36cc6ae5d3 100644
--- a/docs/main/_modules/torch/serialization.html
+++ b/docs/main/_modules/torch/serialization.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/signal/windows/windows.html b/docs/main/_modules/torch/signal/windows/windows.html
index 8155ac0682b0..c7e75d27838b 100644
--- a/docs/main/_modules/torch/signal/windows/windows.html
+++ b/docs/main/_modules/torch/signal/windows/windows.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/sparse.html b/docs/main/_modules/torch/sparse.html
index 1f3caaf04d7c..7913e25cd313 100644
--- a/docs/main/_modules/torch/sparse.html
+++ b/docs/main/_modules/torch/sparse.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/storage.html b/docs/main/_modules/torch/storage.html
index 66e9222e5033..938176077f8f 100644
--- a/docs/main/_modules/torch/storage.html
+++ b/docs/main/_modules/torch/storage.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/testing/_comparison.html b/docs/main/_modules/torch/testing/_comparison.html
index 3fe5f2971ebf..b55bf5d352a7 100644
--- a/docs/main/_modules/torch/testing/_comparison.html
+++ b/docs/main/_modules/torch/testing/_comparison.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/testing/_creation.html b/docs/main/_modules/torch/testing/_creation.html
index 7c7a199b5f64..1ffe6139f8e1 100644
--- a/docs/main/_modules/torch/testing/_creation.html
+++ b/docs/main/_modules/torch/testing/_creation.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils.html b/docs/main/_modules/torch/utils.html
index c3bf0daa5927..fae6936a2008 100644
--- a/docs/main/_modules/torch/utils.html
+++ b/docs/main/_modules/torch/utils.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/backend_registration.html b/docs/main/_modules/torch/utils/backend_registration.html
index f0ccf6908556..10da5472c0db 100644
--- a/docs/main/_modules/torch/utils/backend_registration.html
+++ b/docs/main/_modules/torch/utils/backend_registration.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/benchmark/utils/common.html b/docs/main/_modules/torch/utils/benchmark/utils/common.html
index 83ca9b02672e..957fef30e84c 100644
--- a/docs/main/_modules/torch/utils/benchmark/utils/common.html
+++ b/docs/main/_modules/torch/utils/benchmark/utils/common.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/benchmark/utils/timer.html b/docs/main/_modules/torch/utils/benchmark/utils/timer.html
index 5d746073c6eb..ee19439c7aa3 100644
--- a/docs/main/_modules/torch/utils/benchmark/utils/timer.html
+++ b/docs/main/_modules/torch/utils/benchmark/utils/timer.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.html b/docs/main/_modules/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.html
index 73893e33d7fb..888ce9bcd4f7 100644
--- a/docs/main/_modules/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.html
+++ b/docs/main/_modules/torch/utils/benchmark/utils/valgrind_wrapper/timer_interface.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/checkpoint.html b/docs/main/_modules/torch/utils/checkpoint.html
index 212f04fa3e37..320e775752c8 100644
--- a/docs/main/_modules/torch/utils/checkpoint.html
+++ b/docs/main/_modules/torch/utils/checkpoint.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/cpp_backtrace.html b/docs/main/_modules/torch/utils/cpp_backtrace.html
index 87526e509d6a..9a1357a447ff 100644
--- a/docs/main/_modules/torch/utils/cpp_backtrace.html
+++ b/docs/main/_modules/torch/utils/cpp_backtrace.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/cpp_extension.html b/docs/main/_modules/torch/utils/cpp_extension.html
index 181cceaf141b..001c98719b1d 100644
--- a/docs/main/_modules/torch/utils/cpp_extension.html
+++ b/docs/main/_modules/torch/utils/cpp_extension.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/data/_utils/collate.html b/docs/main/_modules/torch/utils/data/_utils/collate.html
index bafd3413c215..357c99657cc8 100644
--- a/docs/main/_modules/torch/utils/data/_utils/collate.html
+++ b/docs/main/_modules/torch/utils/data/_utils/collate.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/data/_utils/worker.html b/docs/main/_modules/torch/utils/data/_utils/worker.html
index c8c96c684040..e64ba4582d62 100644
--- a/docs/main/_modules/torch/utils/data/_utils/worker.html
+++ b/docs/main/_modules/torch/utils/data/_utils/worker.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/data/dataloader.html b/docs/main/_modules/torch/utils/data/dataloader.html
index 65e5bd30ade9..f54bbff1dd7a 100644
--- a/docs/main/_modules/torch/utils/data/dataloader.html
+++ b/docs/main/_modules/torch/utils/data/dataloader.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/data/dataset.html b/docs/main/_modules/torch/utils/data/dataset.html
index ba7cb037e908..0a38efc5f13e 100644
--- a/docs/main/_modules/torch/utils/data/dataset.html
+++ b/docs/main/_modules/torch/utils/data/dataset.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/data/distributed.html b/docs/main/_modules/torch/utils/data/distributed.html
index 4cbbc73fac2a..baa564070d8a 100644
--- a/docs/main/_modules/torch/utils/data/distributed.html
+++ b/docs/main/_modules/torch/utils/data/distributed.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/data/sampler.html b/docs/main/_modules/torch/utils/data/sampler.html
index 1615ec3dca09..4d3614f09795 100644
--- a/docs/main/_modules/torch/utils/data/sampler.html
+++ b/docs/main/_modules/torch/utils/data/sampler.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/dlpack.html b/docs/main/_modules/torch/utils/dlpack.html
index 826a137526bb..f0da09320062 100644
--- a/docs/main/_modules/torch/utils/dlpack.html
+++ b/docs/main/_modules/torch/utils/dlpack.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/mobile_optimizer.html b/docs/main/_modules/torch/utils/mobile_optimizer.html
index d9acc454aa8c..f9a57904be4b 100644
--- a/docs/main/_modules/torch/utils/mobile_optimizer.html
+++ b/docs/main/_modules/torch/utils/mobile_optimizer.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/utils/tensorboard/writer.html b/docs/main/_modules/torch/utils/tensorboard/writer.html
index e26c6053987b..be6d499b3760 100644
--- a/docs/main/_modules/torch/utils/tensorboard/writer.html
+++ b/docs/main/_modules/torch/utils/tensorboard/writer.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/xpu.html b/docs/main/_modules/torch/xpu.html
index 86503823df55..a6618e8fd4f8 100644
--- a/docs/main/_modules/torch/xpu.html
+++ b/docs/main/_modules/torch/xpu.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/xpu/random.html b/docs/main/_modules/torch/xpu/random.html
index 36020442afb4..7ef32a32ba43 100644
--- a/docs/main/_modules/torch/xpu/random.html
+++ b/docs/main/_modules/torch/xpu/random.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/torch/xpu/streams.html b/docs/main/_modules/torch/xpu/streams.html
index 7d1f398989f1..b0a377093819 100644
--- a/docs/main/_modules/torch/xpu/streams.html
+++ b/docs/main/_modules/torch/xpu/streams.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_modules/typing.html b/docs/main/_modules/typing.html
index 596a3f55cdc5..e1946faaa727 100644
--- a/docs/main/_modules/typing.html
+++ b/docs/main/_modules/typing.html
@@ -242,7 +242,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/_sources/generated/exportdb/index.rst.txt b/docs/main/_sources/generated/exportdb/index.rst.txt
index 3e0e7464f905..da157e95e3b1 100644
--- a/docs/main/_sources/generated/exportdb/index.rst.txt
+++ b/docs/main/_sources/generated/exportdb/index.rst.txt
@@ -19,8 +19,8 @@ support in export please create an issue in the pytorch/pytorch repo wih a modul
     :caption: Tags
 
     torch.escape-hatch
-    torch.dynamic-shape
     torch.cond
+    torch.dynamic-shape
     python.closure
     torch.dynamic-value
     python.data-structure
@@ -203,7 +203,7 @@ cond_branch_class_method
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -284,7 +284,7 @@ cond_branch_nested_function
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -363,7 +363,7 @@ cond_branch_nonlocal_variables
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -528,7 +528,7 @@ cond_operands
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -602,7 +602,7 @@ cond_predicate
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -666,7 +666,7 @@ constrain_as_size_example
 
 .. note::
 
-    Tags: :doc:`torch.escape-hatch `, :doc:`torch.dynamic-value `
+    Tags: :doc:`torch.dynamic-value `, :doc:`torch.escape-hatch `
 
     Support Level: SUPPORTED
 
@@ -726,7 +726,7 @@ constrain_as_value_example
 
 .. note::
 
-    Tags: :doc:`torch.escape-hatch `, :doc:`torch.dynamic-value `
+    Tags: :doc:`torch.dynamic-value `, :doc:`torch.escape-hatch `
 
     Support Level: SUPPORTED
 
@@ -981,7 +981,7 @@ dynamic_shape_if_guard
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`python.control-flow `
+    Tags: :doc:`python.control-flow `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -1027,7 +1027,7 @@ dynamic_shape_map
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.map `
+    Tags: :doc:`torch.map `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -1240,7 +1240,7 @@ list_contains
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`python.assert `, :doc:`python.data-structure `
+    Tags: :doc:`python.assert `, :doc:`torch.dynamic-shape `, :doc:`python.data-structure `
 
     Support Level: SUPPORTED
 
@@ -1286,7 +1286,7 @@ list_unpack
 
 .. note::
 
-    Tags: :doc:`python.data-structure `, :doc:`python.control-flow `
+    Tags: :doc:`python.control-flow `, :doc:`python.data-structure `
 
     Support Level: SUPPORTED
 
@@ -1865,7 +1865,7 @@ dynamic_shape_round
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`python.builtin `
+    Tags: :doc:`python.builtin `, :doc:`torch.dynamic-shape `
 
     Support Level: NOT_SUPPORTED_YET
 
@@ -2005,6 +2005,6 @@ Result:
 
 .. code-block::
 
-    Unsupported: torch.* op returned non-Tensor int call_function 
+    Unsupported: torch.* op returned non-Tensor int call_function 
 
 
diff --git a/docs/main/_sources/generated/exportdb/python.assert.rst.txt b/docs/main/_sources/generated/exportdb/python.assert.rst.txt
index 642ef8752bd3..099c02111476 100644
--- a/docs/main/_sources/generated/exportdb/python.assert.rst.txt
+++ b/docs/main/_sources/generated/exportdb/python.assert.rst.txt
@@ -51,7 +51,7 @@ list_contains
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`python.assert `, :doc:`python.data-structure `
+    Tags: :doc:`python.assert `, :doc:`torch.dynamic-shape `, :doc:`python.data-structure `
 
     Support Level: SUPPORTED
 
diff --git a/docs/main/_sources/generated/exportdb/python.builtin.rst.txt b/docs/main/_sources/generated/exportdb/python.builtin.rst.txt
index 087a65641755..bf475a957e52 100644
--- a/docs/main/_sources/generated/exportdb/python.builtin.rst.txt
+++ b/docs/main/_sources/generated/exportdb/python.builtin.rst.txt
@@ -5,7 +5,7 @@ dynamic_shape_round
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`python.builtin `
+    Tags: :doc:`python.builtin `, :doc:`torch.dynamic-shape `
 
     Support Level: NOT_SUPPORTED_YET
 
diff --git a/docs/main/_sources/generated/exportdb/python.control-flow.rst.txt b/docs/main/_sources/generated/exportdb/python.control-flow.rst.txt
index 71eddb3ee2ad..4eab0b069e30 100644
--- a/docs/main/_sources/generated/exportdb/python.control-flow.rst.txt
+++ b/docs/main/_sources/generated/exportdb/python.control-flow.rst.txt
@@ -5,7 +5,7 @@ dynamic_shape_if_guard
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`python.control-flow `
+    Tags: :doc:`python.control-flow `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -51,7 +51,7 @@ list_unpack
 
 .. note::
 
-    Tags: :doc:`python.data-structure `, :doc:`python.control-flow `
+    Tags: :doc:`python.control-flow `, :doc:`python.data-structure `
 
     Support Level: SUPPORTED
 
diff --git a/docs/main/_sources/generated/exportdb/python.data-structure.rst.txt b/docs/main/_sources/generated/exportdb/python.data-structure.rst.txt
index c31e73dd4316..aeb87fd06137 100644
--- a/docs/main/_sources/generated/exportdb/python.data-structure.rst.txt
+++ b/docs/main/_sources/generated/exportdb/python.data-structure.rst.txt
@@ -116,7 +116,7 @@ list_contains
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`python.assert `, :doc:`python.data-structure `
+    Tags: :doc:`python.assert `, :doc:`torch.dynamic-shape `, :doc:`python.data-structure `
 
     Support Level: SUPPORTED
 
@@ -162,7 +162,7 @@ list_unpack
 
 .. note::
 
-    Tags: :doc:`python.data-structure `, :doc:`python.control-flow `
+    Tags: :doc:`python.control-flow `, :doc:`python.data-structure `
 
     Support Level: SUPPORTED
 
diff --git a/docs/main/_sources/generated/exportdb/torch.cond.rst.txt b/docs/main/_sources/generated/exportdb/torch.cond.rst.txt
index 9f4b4f9d52d1..5852bfe9f23d 100644
--- a/docs/main/_sources/generated/exportdb/torch.cond.rst.txt
+++ b/docs/main/_sources/generated/exportdb/torch.cond.rst.txt
@@ -5,7 +5,7 @@ cond_branch_class_method
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -86,7 +86,7 @@ cond_branch_nested_function
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -165,7 +165,7 @@ cond_branch_nonlocal_variables
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -330,7 +330,7 @@ cond_operands
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -404,7 +404,7 @@ cond_predicate
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
diff --git a/docs/main/_sources/generated/exportdb/torch.dynamic-shape.rst.txt b/docs/main/_sources/generated/exportdb/torch.dynamic-shape.rst.txt
index 96077688e490..9aaa91099655 100644
--- a/docs/main/_sources/generated/exportdb/torch.dynamic-shape.rst.txt
+++ b/docs/main/_sources/generated/exportdb/torch.dynamic-shape.rst.txt
@@ -5,7 +5,7 @@ cond_branch_class_method
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -86,7 +86,7 @@ cond_branch_nested_function
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -165,7 +165,7 @@ cond_branch_nonlocal_variables
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -269,7 +269,7 @@ cond_operands
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -343,7 +343,7 @@ cond_predicate
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.cond `
+    Tags: :doc:`torch.cond `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -451,7 +451,7 @@ dynamic_shape_if_guard
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`python.control-flow `
+    Tags: :doc:`python.control-flow `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -497,7 +497,7 @@ dynamic_shape_map
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.map `
+    Tags: :doc:`torch.map `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
@@ -552,7 +552,7 @@ dynamic_shape_round
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`python.builtin `
+    Tags: :doc:`python.builtin `, :doc:`torch.dynamic-shape `
 
     Support Level: NOT_SUPPORTED_YET
 
@@ -686,7 +686,7 @@ list_contains
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`python.assert `, :doc:`python.data-structure `
+    Tags: :doc:`python.assert `, :doc:`torch.dynamic-shape `, :doc:`python.data-structure `
 
     Support Level: SUPPORTED
 
diff --git a/docs/main/_sources/generated/exportdb/torch.dynamic-value.rst.txt b/docs/main/_sources/generated/exportdb/torch.dynamic-value.rst.txt
index 2a0aea4a5086..432efd9e9f10 100644
--- a/docs/main/_sources/generated/exportdb/torch.dynamic-value.rst.txt
+++ b/docs/main/_sources/generated/exportdb/torch.dynamic-value.rst.txt
@@ -5,7 +5,7 @@ constrain_as_size_example
 
 .. note::
 
-    Tags: :doc:`torch.escape-hatch `, :doc:`torch.dynamic-value `
+    Tags: :doc:`torch.dynamic-value `, :doc:`torch.escape-hatch `
 
     Support Level: SUPPORTED
 
@@ -65,7 +65,7 @@ constrain_as_value_example
 
 .. note::
 
-    Tags: :doc:`torch.escape-hatch `, :doc:`torch.dynamic-value `
+    Tags: :doc:`torch.dynamic-value `, :doc:`torch.escape-hatch `
 
     Support Level: SUPPORTED
 
diff --git a/docs/main/_sources/generated/exportdb/torch.escape-hatch.rst.txt b/docs/main/_sources/generated/exportdb/torch.escape-hatch.rst.txt
index 3791f1365235..70f1b2414b0b 100644
--- a/docs/main/_sources/generated/exportdb/torch.escape-hatch.rst.txt
+++ b/docs/main/_sources/generated/exportdb/torch.escape-hatch.rst.txt
@@ -54,7 +54,7 @@ constrain_as_size_example
 
 .. note::
 
-    Tags: :doc:`torch.escape-hatch `, :doc:`torch.dynamic-value `
+    Tags: :doc:`torch.dynamic-value `, :doc:`torch.escape-hatch `
 
     Support Level: SUPPORTED
 
@@ -114,7 +114,7 @@ constrain_as_value_example
 
 .. note::
 
-    Tags: :doc:`torch.escape-hatch `, :doc:`torch.dynamic-value `
+    Tags: :doc:`torch.dynamic-value `, :doc:`torch.escape-hatch `
 
     Support Level: SUPPORTED
 
diff --git a/docs/main/_sources/generated/exportdb/torch.map.rst.txt b/docs/main/_sources/generated/exportdb/torch.map.rst.txt
index ebcc204972b1..e78e91f902ff 100644
--- a/docs/main/_sources/generated/exportdb/torch.map.rst.txt
+++ b/docs/main/_sources/generated/exportdb/torch.map.rst.txt
@@ -5,7 +5,7 @@ dynamic_shape_map
 
 .. note::
 
-    Tags: :doc:`torch.dynamic-shape `, :doc:`torch.map `
+    Tags: :doc:`torch.map `, :doc:`torch.dynamic-shape `
 
     Support Level: SUPPORTED
 
diff --git a/docs/main/_sources/generated/exportdb/torch.operator.rst.txt b/docs/main/_sources/generated/exportdb/torch.operator.rst.txt
index fd92864c0d49..b1ca776a755a 100644
--- a/docs/main/_sources/generated/exportdb/torch.operator.rst.txt
+++ b/docs/main/_sources/generated/exportdb/torch.operator.rst.txt
@@ -30,4 +30,4 @@ Result:
 
 .. code-block::
 
-    Unsupported: torch.* op returned non-Tensor int call_function 
+    Unsupported: torch.* op returned non-Tensor int call_function 
diff --git a/docs/main/_sources/library.rst.txt b/docs/main/_sources/library.rst.txt
index 4da7485d9856..a17d318cc0ea 100644
--- a/docs/main/_sources/library.rst.txt
+++ b/docs/main/_sources/library.rst.txt
@@ -11,13 +11,21 @@ registration APIs (e.g. aten operators).
 For a detailed guide on effectively using these APIs, please see
 `this gdoc `_
 
-Use :func:`torch.library.define` to define new custom operators. Use the
-impl methods, such as :func:`torch.library.impl` and
+Creating new custom ops in Python
+---------------------------------
+
+Use :func:`torch.library.custom_op` to create new custom ops.
+
+.. autofunction:: custom_op
+
+Extending custom ops created from C++
+-------------------------------------
+
+Use the impl methods, such as :func:`torch.library.impl` and
 func:`torch.library.impl_abstract`, to add implementations
-for any operators (they may have been created using :func:`torch.library.define` or
+for any operators (they may have been created using :func:`torch.library.custom_op` or
 via PyTorch's C++ operator registration APIs).
 
-.. autofunction:: define
 .. autofunction:: impl
 .. autofunction:: impl_abstract
 .. autofunction:: get_ctx
@@ -41,3 +49,5 @@ A tutorial that walks you through some examples on how to use this API is availa
   :members:
 
 .. autofunction:: fallthrough_kernel
+
+.. autofunction:: define
diff --git a/docs/main/amp.html b/docs/main/amp.html
index 47abf438150b..6457c516d608 100644
--- a/docs/main/amp.html
+++ b/docs/main/amp.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/autograd.html b/docs/main/autograd.html
index 5285d19819bb..e3f65796d8c2 100644
--- a/docs/main/autograd.html
+++ b/docs/main/autograd.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/backends.html b/docs/main/backends.html
index 7338a12719f3..52460a68b878 100644
--- a/docs/main/backends.html
+++ b/docs/main/backends.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/benchmark_utils.html b/docs/main/benchmark_utils.html
index 89149a56b79e..2c0507644232 100644
--- a/docs/main/benchmark_utils.html
+++ b/docs/main/benchmark_utils.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/bottleneck.html b/docs/main/bottleneck.html
index 98fe09911f7d..1c91c4292dca 100644
--- a/docs/main/bottleneck.html
+++ b/docs/main/bottleneck.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/checkpoint.html b/docs/main/checkpoint.html
index c9c9ff7f14d4..4f1e97dbfc60 100644
--- a/docs/main/checkpoint.html
+++ b/docs/main/checkpoint.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/community/build_ci_governance.html b/docs/main/community/build_ci_governance.html
index e4c2cec9e3ce..723ca7ae479c 100644
--- a/docs/main/community/build_ci_governance.html
+++ b/docs/main/community/build_ci_governance.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/community/contribution_guide.html b/docs/main/community/contribution_guide.html
index 462837027ea4..15a4c056e715 100644
--- a/docs/main/community/contribution_guide.html
+++ b/docs/main/community/contribution_guide.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/community/design.html b/docs/main/community/design.html
index e8d94ead876c..1ab5ad887818 100644
--- a/docs/main/community/design.html
+++ b/docs/main/community/design.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/community/governance.html b/docs/main/community/governance.html
index e6d4ff9382aa..3c3f28cbb719 100644
--- a/docs/main/community/governance.html
+++ b/docs/main/community/governance.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/community/persons_of_interest.html b/docs/main/community/persons_of_interest.html
index 1e28689bd6b8..b7801980b7e0 100644
--- a/docs/main/community/persons_of_interest.html
+++ b/docs/main/community/persons_of_interest.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/complex_numbers.html b/docs/main/complex_numbers.html
index 09c856bf898e..4cbe370da589 100644
--- a/docs/main/complex_numbers.html
+++ b/docs/main/complex_numbers.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/cond.html b/docs/main/cond.html
index 6792b929ae69..0d6f9b681351 100644
--- a/docs/main/cond.html
+++ b/docs/main/cond.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/config_mod.html b/docs/main/config_mod.html
index c3ab3bcc1f6e..278dbbec43a9 100644
--- a/docs/main/config_mod.html
+++ b/docs/main/config_mod.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/cpp_extension.html b/docs/main/cpp_extension.html
index edebd5468252..283aa653faf7 100644
--- a/docs/main/cpp_extension.html
+++ b/docs/main/cpp_extension.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/cpp_index.html b/docs/main/cpp_index.html
index 7e379857dc4d..44999098da7b 100644
--- a/docs/main/cpp_index.html
+++ b/docs/main/cpp_index.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/cpu.html b/docs/main/cpu.html
index 37dae52d832c..b59f2f2eea25 100644
--- a/docs/main/cpu.html
+++ b/docs/main/cpu.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/cuda._sanitizer.html b/docs/main/cuda._sanitizer.html
index d241f1c051b9..815748dabc64 100644
--- a/docs/main/cuda._sanitizer.html
+++ b/docs/main/cuda._sanitizer.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/cuda.html b/docs/main/cuda.html
index 8d90325942cd..b7d9128681db 100644
--- a/docs/main/cuda.html
+++ b/docs/main/cuda.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/cuda_environment_variables.html b/docs/main/cuda_environment_variables.html
index 77694f79050e..1d5efc65ba2c 100644
--- a/docs/main/cuda_environment_variables.html
+++ b/docs/main/cuda_environment_variables.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/cudnn_persistent_rnn.html b/docs/main/cudnn_persistent_rnn.html
index 0b3f490cf18d..44061fc84ece 100644
--- a/docs/main/cudnn_persistent_rnn.html
+++ b/docs/main/cudnn_persistent_rnn.html
@@ -241,7 +241,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/cudnn_rnn_determinism.html b/docs/main/cudnn_rnn_determinism.html
index 22ca6c37f688..5b3a66b7ceac 100644
--- a/docs/main/cudnn_rnn_determinism.html
+++ b/docs/main/cudnn_rnn_determinism.html
@@ -241,7 +241,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/data.html b/docs/main/data.html
index 10dbc4b16ef7..25f8fec206d0 100644
--- a/docs/main/data.html
+++ b/docs/main/data.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/ddp_comm_hooks.html b/docs/main/ddp_comm_hooks.html
index f462d0779dc8..f367c30a8f6f 100644
--- a/docs/main/ddp_comm_hooks.html
+++ b/docs/main/ddp_comm_hooks.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/debugging_environment_variables.html b/docs/main/debugging_environment_variables.html
index 27dae08cafd5..16035fe6813b 100644
--- a/docs/main/debugging_environment_variables.html
+++ b/docs/main/debugging_environment_variables.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/deploy.html b/docs/main/deploy.html
index 8cc8df1c4fbb..e5576b4995e1 100644
--- a/docs/main/deploy.html
+++ b/docs/main/deploy.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/deterministic.html b/docs/main/deterministic.html
index 93033f861ee0..c25c044aaa91 100644
--- a/docs/main/deterministic.html
+++ b/docs/main/deterministic.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/distributed.algorithms.join.html b/docs/main/distributed.algorithms.join.html
index c813f6253895..87fb6b0ac760 100644
--- a/docs/main/distributed.algorithms.join.html
+++ b/docs/main/distributed.algorithms.join.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/distributed.checkpoint.html b/docs/main/distributed.checkpoint.html
index 68cf83283573..5f776edc2931 100644
--- a/docs/main/distributed.checkpoint.html
+++ b/docs/main/distributed.checkpoint.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/distributed.elastic.html b/docs/main/distributed.elastic.html
index f74dc9087468..662653029804 100644
--- a/docs/main/distributed.elastic.html
+++ b/docs/main/distributed.elastic.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/distributed.html b/docs/main/distributed.html
index 2eaba0ee06e3..8859b602cb2e 100644
--- a/docs/main/distributed.html
+++ b/docs/main/distributed.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/distributed.optim.html b/docs/main/distributed.optim.html
index 11b5023b68c5..bd6d32a096df 100644
--- a/docs/main/distributed.optim.html
+++ b/docs/main/distributed.optim.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/distributed.tensor.parallel.html b/docs/main/distributed.tensor.parallel.html
index ff9634f5ec87..e0178e796300 100644
--- a/docs/main/distributed.tensor.parallel.html
+++ b/docs/main/distributed.tensor.parallel.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/distributions.html b/docs/main/distributions.html
index 640d4afabead..7e437db903c2 100644
--- a/docs/main/distributions.html
+++ b/docs/main/distributions.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/dlpack.html b/docs/main/dlpack.html
index 679084c42d2c..b3d87cc6811f 100644
--- a/docs/main/dlpack.html
+++ b/docs/main/dlpack.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/agent.html b/docs/main/elastic/agent.html
index b9a1c0a15b60..0a36a47ac5ac 100644
--- a/docs/main/elastic/agent.html
+++ b/docs/main/elastic/agent.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/customization.html b/docs/main/elastic/customization.html
index fcc0210170c2..b33b7143c1ad 100644
--- a/docs/main/elastic/customization.html
+++ b/docs/main/elastic/customization.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/errors.html b/docs/main/elastic/errors.html
index e8ba7df8485e..f7bf0f5de2c2 100644
--- a/docs/main/elastic/errors.html
+++ b/docs/main/elastic/errors.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/events.html b/docs/main/elastic/events.html
index 56234a4c399d..84a661eaa5cd 100644
--- a/docs/main/elastic/events.html
+++ b/docs/main/elastic/events.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/examples.html b/docs/main/elastic/examples.html
index e6e81edb5cf2..81632e9222c4 100644
--- a/docs/main/elastic/examples.html
+++ b/docs/main/elastic/examples.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/kubernetes.html b/docs/main/elastic/kubernetes.html
index f596c6565539..27215a94a654 100644
--- a/docs/main/elastic/kubernetes.html
+++ b/docs/main/elastic/kubernetes.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/metrics.html b/docs/main/elastic/metrics.html
index b87047006476..6c75aa8faa57 100644
--- a/docs/main/elastic/metrics.html
+++ b/docs/main/elastic/metrics.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/multiprocessing.html b/docs/main/elastic/multiprocessing.html
index 8118ab249b0e..770bfef8293f 100644
--- a/docs/main/elastic/multiprocessing.html
+++ b/docs/main/elastic/multiprocessing.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/quickstart.html b/docs/main/elastic/quickstart.html
index 58dd87d591bf..18d13a0655da 100644
--- a/docs/main/elastic/quickstart.html
+++ b/docs/main/elastic/quickstart.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/rendezvous.html b/docs/main/elastic/rendezvous.html
index 365957abf066..14d1c1899605 100644
--- a/docs/main/elastic/rendezvous.html
+++ b/docs/main/elastic/rendezvous.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/run.html b/docs/main/elastic/run.html
index bf4b07512f62..2d81d0d63ac6 100644
--- a/docs/main/elastic/run.html
+++ b/docs/main/elastic/run.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/subprocess_handler.html b/docs/main/elastic/subprocess_handler.html
index 19ae093d27f2..e59af70fa3f0 100644
--- a/docs/main/elastic/subprocess_handler.html
+++ b/docs/main/elastic/subprocess_handler.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/timer.html b/docs/main/elastic/timer.html
index 6b0661e8d473..7041571f0477 100644
--- a/docs/main/elastic/timer.html
+++ b/docs/main/elastic/timer.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/elastic/train_script.html b/docs/main/elastic/train_script.html
index 9ca1e94ad9a3..13069e847a60 100644
--- a/docs/main/elastic/train_script.html
+++ b/docs/main/elastic/train_script.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/export.html b/docs/main/export.html
index 88a0861868ef..8651c3f06b83 100644
--- a/docs/main/export.html
+++ b/docs/main/export.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/export.ir_spec.html b/docs/main/export.ir_spec.html
index d87ab61d0a2a..8cfb403a2067 100644
--- a/docs/main/export.ir_spec.html
+++ b/docs/main/export.ir_spec.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/fft.html b/docs/main/fft.html
index a0808d36af9d..f153b43fc4db 100644
--- a/docs/main/fft.html
+++ b/docs/main/fft.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
diff --git a/docs/main/fsdp.html b/docs/main/fsdp.html
index 4d569a7e0e6c..4514b1d967d1 100644
--- a/docs/main/fsdp.html
+++ b/docs/main/fsdp.html
@@ -243,7 +243,7 @@
           

             
     

-      main (2.4.0a0+git31aff29 ) ▼
+      main (2.4.0a0+git064a650 ) ▼
     

     
 
@@ -488,7 +488,8 @@
 
A wrapper for sharding module parameters across data parallel workers.

 
This is inspired by Xu et al. as well as the ZeRO Stage 3 from DeepSpeed.
 FullyShardedDataParallel is commonly shortened to FSDP.

-
For advanced notes please refer to FSDP Notes.

+
To understand FSDP internals, refer to the
+FSDP Notes.

 
Example:

 
>>> import torch
 >>> from torch.distributed.fsdp import FullyShardedDataParallel as FSDP
@@ -501,127 +502,78 @@
 >>> optim.step()
 

 

-

-
Warning

-
The optimizer must be initialized after the module has been wrapped
-with FSDP since FSDP will shard and transform the module’s parameters
-in a way that may not preserve the original parameter variables. Thus,
-the previously initialized optimizer may have stale references to the
-parameters.

-

-

-
Warning

-
If the destination CUDA device has ID dev_id, either (1)
-module should already be placed on that device, (2) the device
-should be set using torch.cuda.set_device(dev_id), or (3)
-dev_id should be passed into the device_id constructor
-argument. This FSDP instance’s compute device will be that destination
-device. For (1) and (3), the FSDP initialization always occurs on GPU.
-For (2), the FSDP initialization happens on module ‘s current
-device, which may be CPU.

-

-

-
Warning

-
FSDP currently does not support gradient accumulation outside
-no_sync() when using CPU offloading. Trying to do so yields
-incorrect results since FSDP will use the newly-reduced gradient
-instead of accumulating with any existing gradient.

-

-

-
Warning

-
Changing the original parameter variable names after construction will
-lead to undefined behavior.

-

-

-
Warning

-
Passing in the sync_module_states=True flag requires module to
-be on GPU or to use the device_id argument to specify a CUDA device
-that FSDP will move module to in the FSDP constructor. This is
-because sync_module_states=True requires GPU communication.

-

-

-
Warning

-
As of PyTorch 1.12, FSDP only offers limited support for shared parameters
-(for example, setting one Linear layer’s weight to another’s). In
-particular, modules that share parameters must be wrapped as part of the
-same FSDP unit. If enhanced shared parameter support is needed for your
-use case, please ping https://github.com/pytorch/pytorch/issues/77724

-

-

-
Warning

-
FSDP has some constraints on freezing parameters (i.e. setting
-param.requires_grad=False). For use_orig_params=False, each
-FSDP instance must manage parameters that are all frozen or all
-non-frozen. For use_orig_params=True, FSDP supports mixing frozen
-and non-frozen, but we recommend not doing so since then the gradient
-memory usage will be higher than expected (namely, equivalent to not
-freezing those parameters). This means that ideally, frozen parameters
-should be isolated into their own nn.Module s and wrapped
-separately with FSDP.

-

-

-
Note

-
Attempting to run the forward pass of a submodule that is contained in an
-FSDP instance is not supported and will result in errors. This is because the
-submodule’s parameters will be sharded, but it itself is not an FSDP instance,
-so its forward pass will not all-gather the full parameters appropriately.
-This could potentially happen when attempting to run only the encoder of a
-encoder-decoder model, and the encoder is not wrapped in its own FSDP instance. To
-resolve this, please wrap the submodule in its own FSDP unit.

-

-

-
Note

-
FSDP moves input tensors to the forward method to the GPU compute
-device, so the user does not need to manually move them from CPU.

-

-

-
Warning

-
The user should not modify the parameters between forward and backward
-without using the summon_full_params() context since the
-modifications may not persist. Moreover, for use_orig_params=False,
-accessing the original parameters between forward and backward may
-raise an illegal memory access.

-

-

-
Warning

-
For use_orig_params=True, ShardingStrategy.SHARD_GRAD_OP
-exposes the unsharded parameters, not the sharded parameters, after
-forward since it does not free the unsharded ones, unlike
-ShardingStrategy.FULL_SHARD. One caveat is that, since gradients
-are always sharded or None, ShardingStrategy.SHARD_GRAD_OP will
-not expose the sharded gradients with the unsharded parameters after
-forward. If you want to inspect the gradients, try
-summon_full_params() with with_grads=True.

-

-

-
Warning

-
FSDP replaces managed modules’ parameters with torch.Tensor views
-during forward and backward computation for autograd-related reasons.
-If your module’s forward relies on saved references to the parameters
-instead of reacquiring the references each iteration, then it will not
-see FSDP’s newly created views, and autograd will not work correctly.

-

-

-
Note

+
Using FSDP involves wrapping your module and then initializing your
+optimizer after. This is required since FSDP changes the parameter
+variables.

+
When setting up FSDP, you need to consider the destination CUDA
+device. If the device has an ID (dev_id), you have three options:

+
    
+
  • Place the module on that device
    • 
+
  • Set the device using torch.cuda.set_device(dev_id)
    • 
+
  • Pass dev_id into the device_id constructor argument.
    • 
+

+
This ensures that the FSDP instance’s compute device is the
+destination device. For option 1 and 3, the FSDP initialization
+always occurs on GPU. For option 2, the FSDP initialization
+happens on module’s current device, which may be a CPU.

+
If you’re using the sync_module_states=True flag, you need to
+ensure that the module is on a GPU or use the device_id
+argument to specify a CUDA device that FSDP will move the module
+to in the FSDP constructor. This is necessary because
+sync_module_states=True requires GPU communication.

+
FSDP also takes care of moving input tensors to the forward method
+to the GPU compute device, so you don’t need to manually move them
+from CPU.

+
For use_orig_params=True,
+ShardingStrategy.SHARD_GRAD_OP exposes the unsharded
+parameters, not the sharded parameters after forward, unlike
+ShardingStrategy.FULL_SHARD. If you want
+to inspect the gradients, you can use the summon_full_params
+method with with_grads=True.

 
With limit_all_gathers=True, you may see a gap in the FSDP
 pre-forward where the CPU thread is not issuing any kernels. This is
 intentional and shows the rate limiter in effect. Synchronizing the CPU
 thread in that way prevents over-allocating memory for subsequent
 all-gathers, and it should not actually delay GPU kernel execution.

-

-

-
Note

-
When using sharding_strategy=ShardingStrategy.HYBRID_SHARD with the
-sharding process group being intra-node and the replication process
-group being inter-node, setting NCCL_CROSS_NIC=1 can help improve
-the all-reduce times over the replication process group for some
-cluster setups.

-

-

-
Warning

-
FSDP does not work with double backwards due to how it registers
-backward hooks.

-

+
FSDP replaces managed modules’ parameters with torch.Tensor
+views during forward and backward computation for autograd-related
+reasons. If your module’s forward relies on saved references to
+the parameters instead of reacquiring the references each
+iteration, then it will not see FSDP’s newly created views,
+and autograd will not work correctly.

+
Finally, when using sharding_strategy=ShardingStrategy.HYBRID_SHARD
+with the sharding process group being intra-node and the
+replication process group being inter-node, setting
+NCCL_CROSS_NIC=1 can help improve the all-reduce times over
+the replication process group for some cluster setups.

+
Limitations

+
There are several limitations to be aware of when using FSDP:

+
    
+
  • FSDP currently does not support gradient accumulation outside
+no_sync() when using CPU offloading. This is because FSDP
+uses the newly-reduced gradient instead of accumulating with any
+existing gradient, which can lead to incorrect results.
    • 
+
  • FSDP does not support running the forward pass of a submodule
+that is contained in an FSDP instance. This is because the
+submodule’s parameters will be sharded, but the submodule itself
+is not an FSDP instance, so its forward pass will not all-gather
+the full parameters appropriately.
    • 
+
  • FSDP does not work with double backwards due to the way it
+registers backward hooks.
    • 
+
  • FSDP has some constraints when freezing parameters.
+For use_orig_params=False, each FSDP instance must manage
+parameters that are all frozen or all non-frozen. For
+use_orig_params=True, FSDP supports mixing frozen and
+non-frozen parameters, but it’s recommended to avoid doing so to
+prevent higher than expected gradient memory usage.
    • 
+
  • As of PyTorch 1.12, FSDP offers limited support for shared
+parameters. If enhanced shared parameter support is needed for
+your use case, please post in
+this issue.
    • 
+
  • You should avoid modifying the parameters between forward and
+backward without using the summon_full_params context, as
+the modifications may not persist.
    • 
+

 

 
Parameters

 
    
@@ -833,28 +785,19 @@
 
    Tensor
    
 
    
 

-

-
Note

 
If every FSDP instance uses NO_SHARD, meaning that no
 gradients are sharded across ranks, then you may directly use
 torch.nn.utils.clip_grad_norm_().

-

-

-
Note

 
If at least some FSDP instance uses a sharded strategy (i.e.
 one other than NO_SHARD), then you should use this method
 instead of torch.nn.utils.clip_grad_norm_() since this method
 handles the fact that gradients are sharded across ranks.

-

-

-
Note

 
The total norm returned will have the “largest” dtype across
 all parameters/gradients as defined by PyTorch’s type promotion
 semantics. For example, if all parameters/gradients use a low
 precision dtype, then the returned norm’s dtype will be that low
 precision dtype, but if there exists at least one parameter/
 gradient using FP32, then the returned norm’s dtype will be FP32.

-

 

 
Warning

 
This needs to be called on all ranks since it uses
@@ -934,26 +877,17 @@
 torch.optim.Optimizer.state_dict(), i.e. with keys "state"
 and "param_groups". The flattened parameters in FSDP modules
 contained in model are mapped back to their unflattened parameters.

-

-
Warning

 
This needs to be called on all ranks since it uses
 collective communications. However, if rank0_only=True, then
 the state dict is only populated on rank 0, and all other ranks
 return an empty dict.

-

-

-
Warning

 
Unlike torch.optim.Optimizer.state_dict(), this method
 uses full parameter names as keys instead of parameter IDs.

-

-

-
Note

 
Like in torch.optim.Optimizer.state_dict(), the tensors
 contained in the optimizer state dict are not cloned, so there may
 be aliasing surprises. For best practices, consider saving the
 returned optimizer state dict immediately, e.g. using
 torch.save().

-

 

 
Parameters