v4.1 release update v2. (#2481)

This commit is contained in:
Junkai-Wu
2025-07-22 10:03:55 +08:00
committed by GitHub
parent 9baa06dd57
commit fd6cfe1ed0
179 changed files with 7878 additions and 1286 deletions

View File

@ -256,16 +256,6 @@
" cute.printf(\"a[2,3] = {}\", a[2,3])\n",
" cute.printf(\"a[(2,4)] = {}\", a[(2,4)])\n",
"\n",
"@cute.kernel\n",
"def print_tensor_gpu(ptr: cute.Pointer):\n",
" layout = cute.make_layout((8, 5), stride=(5, 1))\n",
" tensor = cute.make_tensor(ptr, layout)\n",
"\n",
" tidx, _, _ = cute.arch.thread_idx()\n",
"\n",
" if tidx == 0:\n",
" cute.print_tensor(tensor)\n",
"\n",
"\n",
"# Create a tensor with sequential data using torch\n",
"data = torch.arange(0, 8*5, dtype=torch.float32).reshape(8, 5)\n",