leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 28 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/print.ipynb
+28 -17
View File
@@ -83,8 +83,8 @@
" print(\">>>\", type(b)) # => <class 'int'>\n",
"\n",
" layout = cute.make_layout((a, b))\n",
" print(\">>>\", layout) # => (?,2):(1,?)\n",
" cute.printf(\">?? {}\", layout) # => (8,2):(1,8)"
" print(\">>>\", layout) # => (?,2):(1,?)\n",
" cute.printf(\">?? {}\", layout) # => (8,2):(1,8)"
]
},
{
@@ -221,6 +221,7 @@
" layout = cute.make_layout((a, b))\n",
" print(f\"layout: {layout}\")\n",
"\n",
"\n",
"print(\"Direct run output:\")\n",
"format_string_example(cutlass.Int32(8), 2)"
]
@@ -246,23 +247,26 @@
"source": [
"from cutlass.cute.runtime import from_dlpack\n",
"\n",
"\n",
"@cute.jit\n",
"def print_tensor_basic(x : cute.Tensor):\n",
"def print_tensor_basic(x: cute.Tensor):\n",
" # Print the tensor\n",
" print(\"Basic output:\")\n",
" cute.print_tensor(x)\n",
" \n",
"\n",
"\n",
"@cute.jit\n",
"def print_tensor_verbose(x : cute.Tensor):\n",
"def print_tensor_verbose(x: cute.Tensor):\n",
" # Print the tensor with verbose mode\n",
" print(\"Verbose output:\")\n",
" cute.print_tensor(x, verbose=True)\n",
"\n",
"\n",
"@cute.jit\n",
"def print_tensor_slice(x : cute.Tensor, coord : tuple):\n",
"def print_tensor_slice(x: cute.Tensor, coord: tuple):\n",
" # slice a 2D tensor from the 3D tensor\n",
" sliced_data = cute.slice_(x, coord)\n",
" y = cute.make_fragment(sliced_data.layout, sliced_data.element_type)\n",
" y = cute.make_rmem_tensor(sliced_data.layout, sliced_data.element_type)\n",
" # Convert to TensorSSA format by loading the sliced data into the fragment\n",
" y.store(sliced_data.load())\n",
" print(\"Slice output:\")\n",
@@ -302,12 +306,13 @@
"source": [
"def tensor_print_example1():\n",
" shape = (4, 3, 2)\n",
" \n",
"\n",
" # Creates [0,...,23] and reshape to (4, 3, 2)\n",
" data = np.arange(24, dtype=np.float32).reshape(*shape) \n",
" \n",
" data = np.arange(24, dtype=np.float32).reshape(*shape)\n",
"\n",
" print_tensor_basic(from_dlpack(data))\n",
"\n",
"\n",
"tensor_print_example1()"
]
},
@@ -348,12 +353,13 @@
"source": [
"def tensor_print_example2():\n",
" shape = (4, 3)\n",
" \n",
"\n",
" # Creates [0,...,11] and reshape to (4, 3)\n",
" data = np.arange(12, dtype=np.float32).reshape(*shape) \n",
" \n",
" data = np.arange(12, dtype=np.float32).reshape(*shape)\n",
"\n",
" print_tensor_verbose(from_dlpack(data))\n",
"\n",
"\n",
"tensor_print_example2()"
]
},
@@ -390,13 +396,14 @@
"source": [
"def tensor_print_example3():\n",
" shape = (4, 3)\n",
" \n",
"\n",
" # Creates [0,...,11] and reshape to (4, 3)\n",
" data = np.arange(12, dtype=np.float32).reshape(*shape) \n",
" \n",
" data = np.arange(12, dtype=np.float32).reshape(*shape)\n",
"\n",
" print_tensor_slice(from_dlpack(data), (None, 0))\n",
" print_tensor_slice(from_dlpack(data), (1, None))\n",
"\n",
"\n",
"tensor_print_example3()"
]
},
@@ -418,9 +425,10 @@
" print(src)\n",
" cute.print_tensor(src)\n",
"\n",
"\n",
"@cute.jit\n",
"def print_tensor_host(src: cute.Tensor):\n",
" print_tensor_gpu(src).launch(grid=(1,1,1), block=(1,1,1))"
" print_tensor_gpu(src).launch(grid=(1, 1, 1), block=(1, 1, 1))"
]
},
{
@@ -449,11 +457,14 @@
],
"source": [
"import torch\n",
"\n",
"\n",
"def tensor_print_example4():\n",
" a = torch.randn(4, 3, device=\"cuda\")\n",
" cutlass.cuda.initialize_cuda_context()\n",
" print_tensor_host(from_dlpack(a))\n",
"\n",
"\n",
"tensor_print_example4()"
]
},