CUTLASS 3.4.0 (#1286)

* CUTLASS 3.4.0

* Update CHANGELOG.md

---------

Co-authored-by: Pradeep Ramani <prramani@nvidia.com>

examples/python/02_pytorch_extension_grouped_gemm.ipynb

@@ -134,7 +134,7 @@
    "id": "590a3bc5",
    "metadata": {},
    "source": [
-    "We'll next run a group of 50 GEMMs via the CUTLASS Python interface and via PyTorch."
+    "We'll next run a group of 20 GEMMs via the CUTLASS Python interface and via PyTorch."
    ]
   },
   {
@@ -144,7 +144,7 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "As, Bs, Cs, Ds, = generate_problems(50)\n",
+    "As, Bs, Cs, Ds, = generate_problems(20)\n",
     "\n",
     "plan.run(As, Bs, Cs, Ds, print_module=True)\n",
     "Ds_torch = [a @ b for a, b in zip(As, Bs)]\n",