v4.0 update. (#2371)

examples/python/CuTeDSL/notebooks/hello_world.ipynb

@@ -83,11 +83,6 @@
     "\n",
     "    # Print hello world from host code\n",
     "    cute.printf(\"hello world\")\n",
-    "    \n",
-    "    # Initialize CUDA context for launching a kernel with error checking\n",
-    "    # We make context initialization explicit to allow users to control the context creation \n",
-    "    # and avoid potential issues with multiple contexts\n",
-    "    cutlass.cuda.initialize_cuda_context()\n",
     "\n",
     "    # Launch kernel\n",
     "    kernel().launch(\n",
@@ -129,6 +124,11 @@
     }
    ],
    "source": [
+    "# Initialize CUDA context for launching a kernel with error checking\n",
+    "# We make context initialization explicit to allow users to control the context creation \n",
+    "# and avoid potential issues with multiple contexts\n",
+    "cutlass.cuda.initialize_cuda_context()\n",
+    "\n",
     "# Method 1: Just-In-Time (JIT) compilation - compiles and runs the code immediately\n",
     "print(\"Running hello_world()...\")\n",
     "hello_world()\n",
@@ -136,6 +136,7 @@
     "# Method 2: Compile first (useful if you want to run the same code multiple times)\n",
     "print(\"Compiling...\")\n",
     "hello_world_compiled = cute.compile(hello_world)\n",
+    "\n",
     "# Run the pre-compiled version\n",
     "print(\"Running compiled version...\")\n",
     "hello_world_compiled()"