Release v4.0.0 (#2294)

2025-05-13 15:55:29 -04:00
parent ad7b2f5e84
commit f115c3f854
299 changed files with 51495 additions and 4413 deletions
@@ -0,0 +1,18 @@
+.. _cute_nvgpu:
+
+cutlass.cute.nvgpu
+==================
+
+The ``cute.nvgpu`` module contains MMA and Copy Operations as well as Operation-specific helper
+functions. The arch-agnostic Operations are exposed at the top-level while arch-specific Operations
+are grouped into submodules like ``tcgen05``.
+
+.. toctree::
+  :maxdepth: 2
+  :hidden:
+
+  cute_nvgpu_common
+  cute_nvgpu_warp
+  cute_nvgpu_warpgroup
+  cute_nvgpu_cpasync
+  cute_nvgpu_tcgen05