v4.2 release. (#2587)

* Fix default cluster callback values to 1 to avoid profiler failure when these values are not set in command line.

* v4.2 release.

examples/python/deprecated/02_pytorch_extension_grouped_gemm.ipynb

@@ -75,7 +75,7 @@
     "\n",
     "## Declaring a grouped GEMM via the CUTLASS Python interface\n",
     "A grouped GEMM operation is declared similarly to a GEMM operation in the CUTLASS Python interface: one\n",
-    "simply calls `cutlass.op.GroupedGemm`."
+    "simply calls `cutlass_cppgen.op.GroupedGemm`."
    ]
   },
   {
@@ -85,11 +85,11 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "import cutlass\n",
+    "import cutlass_cppgen\n",
     "import torch\n",
     "\n",
     "dtype = torch.float16\n",
-    "plan = cutlass.op.GroupedGemm(element=dtype, layout=cutlass.LayoutType.RowMajor)"
+    "plan = cutlass_cppgen.op.GroupedGemm(element=dtype, layout=cutlass_cppgen.LayoutType.RowMajor)"
    ]
   },
   {
@@ -174,7 +174,7 @@
    "outputs": [],
    "source": [
     "op = plan.construct()\n",
-    "grouped_gemm = cutlass.emit.pytorch(op, name='grouped_gemm', cc=plan.cc, sourcedir='out', jit=True)"
+    "grouped_gemm = cutlass_cppgen.emit.pytorch(op, name='grouped_gemm', cc=plan.cc, sourcedir='out', jit=True)"
    ]
   },
   {
@@ -182,7 +182,7 @@
    "id": "c8ca3991",
    "metadata": {},
    "source": [
-    "The `cutlass.emit.pytorch` function emits:\n",
+    "The `cutlass_cppgen.emit.pytorch` function emits:\n",
     "* `out/grouped_gemm_kernel.cu`: This file contains the declaration of the CUTLASS kernel and a method to call it from PyTorch tensors\n",
     "* `out/grouped_gemm.cpp`: This file contains a C++ wrapper around the aforementioned CUTLASS kernel\n",
     "* `setup.py`: This file contains the `setuptools` script for building and installing the generated extension\n",