Merge branch 'main' into patch-1

Author: Svetlana Karslioglu

intermediate_source/torch_compile_tutorial.py

@@ -33,9 +33,25 @@
 # - ``numpy``
 # - ``scipy``
 # - ``tabulate``
-#
-# Note: a modern NVIDIA GPU (Volta or Ampere) is recommended for this tutorial.
-#
+
+######################################################################
+# NOTE: a modern NVIDIA GPU (H100, A100, or V100) is recommended for this tutorial in
+# order to reproduce the speedup numbers shown below and documented elsewhere.
+
+import torch
+import warnings
+
+gpu_ok = False
+if torch.cuda.is_available():
+    device_cap = torch.cuda.get_device_capability()
+    if device_cap in ((7, 0), (8, 0), (9, 0)):
+        gpu_ok = True
+
+if not gpu_ok:
+    warnings.warn(
+        "GPU is not NVIDIA V100, A100, or H100. Speedup numbers may be lower "
+        "than expected."
+    )
 
 ######################################################################
 # Basic Usage
@@ -51,8 +67,6 @@
 # ``torch.compile``. We can then call the returned optimized
 # function in place of the original function.
 
-import torch
-
 def foo(x, y):
     a = torch.sin(x)
     b = torch.cos(x)