leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 27 Packages Projects Releases Wiki Activity

v4.3 update. (#2709)

Browse Source 
* v4.3 update.

* Update the cute_dsl_api changelog's doc link

* Update version to 4.3.0

* Update the example link

* Update doc to encourage user to install DSL from requirements.txt

---------

Co-authored-by: Larry Wu <larwu@nvidia.com>
This commit is contained in:
Junkai-Wu
2025-10-21 14:26:30 -04:00
committed by GitHub
co-authored by Larry Wu
parent e6e2cc29f5
commit b1d6e2c9b3
244 changed files with 59272 additions and 10455 deletions
Download Patch File Download Diff File Expand all files Collapse all files
examples/python/CuTeDSL/notebooks/hello_world.ipynb
+18 -9
View File
@@ -27,8 +27,8 @@
"metadata": {},
"outputs": [],
"source": [
"import cutlass \n",
"import cutlass.cute as cute "
"import cutlass\n",
"import cutlass.cute as cute"
]
},
{
@@ -80,14 +80,13 @@
"source": [
"@cute.jit\n",
"def hello_world():\n",
"\n",
" # Print hello world from host code\n",
" cute.printf(\"hello world\")\n",
"\n",
" # Launch kernel\n",
" kernel().launch(\n",
" grid=(1, 1, 1), # Single thread block\n",
" block=(32, 1, 1) # One warp (32 threads) per thread block\n",
" grid=(1, 1, 1), # Single thread block\n",
" block=(32, 1, 1), # One warp (32 threads) per thread block\n",
" )"
]
},
@@ -107,7 +106,7 @@
},
{
"cell_type": "code",
"execution_count": 4,
"execution_count": 5,
"metadata": {},
"outputs": [
{
@@ -115,17 +114,19 @@
"output_type": "stream",
"text": [
"Running hello_world()...\n",
"hello world\n",
"Compiling...\n",
"hello world\n",
"Hello world\n",
"Compiling with PTX/CUBIN dumped...\n",
"Running compiled version...\n",
"hello world\n"
"hello world\n",
"Hello world\n"
]
}
],
"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",
"# 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",
@@ -137,6 +138,14 @@
"print(\"Compiling...\")\n",
"hello_world_compiled = cute.compile(hello_world)\n",
"\n",
"# Dump PTX/CUBIN files while compiling\n",
"from cutlass.cute import KeepPTX, KeepCUBIN\n",
"\n",
"print(\"Compiling with PTX/CUBIN dumped...\")\n",
"# Alternatively, compile with string based options like\n",
"# cute.compile(hello_world, options=\"--keep-ptx --keep-cubin\") would also work.\n",
"hello_world_compiled_ptx_on = cute.compile[KeepPTX, KeepCUBIN](hello_world)\n",
"\n",
"# Run the pre-compiled version\n",
"print(\"Running compiled version...\")\n",
"hello_world_compiled()"