CUTLASS 3.2 (#1024)

* CUTLASS 3.2

examples/python/02_pytorch_extension_grouped_gemm.ipynb

@@ -8,7 +8,7 @@
    "source": [
     "# Exporting a CUTLASS grouped GEMM kernel to a PyTorch CUDA extension\n",
     "This notebook walks through a basic example of using the CUTLASS Python interface to declare\n",
-    "a grouped GEMM kernel and export it as a PyTorch CUDA extension.\n",
+    "a grouped GEMM kernel and export it as a PyTorch CUDA extension. Note that GEMM and Conv2d can also be exported as PyTorch CUDA extensions. \n",
     "\n",
     "[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/NVIDIA/cutlass/tree/master/examples/00_basic_gemm.ipynb)\n",
     "\n",
@@ -230,14 +230,6 @@
     "print('Non-Grouped: {:.3f} us'.format(nongrouped * 1e6/num_profile))\n",
     "print('Speedup: {:.3f}'.format(nongrouped / grouped))"
    ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": null,
-   "id": "f22fc696",
-   "metadata": {},
-   "outputs": [],
-   "source": []
   }
  ],
  "metadata": {