v4.4 tag release update. (#3032)

2026-02-14 12:27:58 +08:00
parent 01687cfba1
commit d4bbf728ca
140 changed files with 41624 additions and 3691 deletions
--- a/examples/python/CuTeDSL/ampere/smem_allocator.py
+++ b/examples/python/CuTeDSL/ampere/smem_allocator.py
@@ -28,7 +28,6 @@

 import cutlass.cute as cute
 import cutlass
-import torch
 import numpy as np
 from cutlass.cute.runtime import from_dlpack

@@ -175,6 +174,8 @@ def host(


 def run_and_verify(const_a, const_b, const_c):
+    import torch
+
    dst_a = torch.zeros((8, 4), dtype=torch.float32, device="cuda")
    dst_b = torch.zeros((8, 2), dtype=torch.float32, device="cuda")
    dst_c = torch.zeros((16, 2), dtype=torch.float32, device="cuda")