Release v4.0.0 (#2294)

media/docs/pythonDSL/cute_dsl_api/cute.rst

@@ -0,0 +1,11 @@
+.. _cute:
+
+cutlass.cute
+============
+
+.. automodule:: cutlass.cute
+   :members:
+   :undoc-members:
+   :show-inheritance:
+   :special-members: __init__
+   :private-members:

media/docs/pythonDSL/cute_dsl_api/cute_arch.rst

@@ -0,0 +1,24 @@
+.. _cute_arch:
+
+cutlass.cute.arch
+=================
+
+The ``cute.arch`` module contains wrappers around NVVM-level MLIR Op builders that seamlessly
+inter-operate with the Python types used in CUTLASS Python. Another benefit of wrapping these Op
+builders is that the source location can be tracked with the ``@dsl_user_op`` decorator. Available
+functions include
+
+- basic API like ``thr_idx``;
+- functions related to the direct management of mbarriers;
+- low-level SMEM management (prefer using the ``SmemAllocator`` class);
+- TMEM management.
+
+API documentation
+-----------------
+
+.. automodule:: cutlass.cute.arch
+   :members:
+   :undoc-members:
+   :show-inheritance:
+   :special-members: __init__
+   :private-members:

media/docs/pythonDSL/cute_dsl_api/cute_nvgpu.rst

@@ -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

media/docs/pythonDSL/cute_dsl_api/cute_nvgpu_common.rst

@@ -0,0 +1,9 @@
+.. _cute_nvgpu_common:
+
+Common
+======
+
+.. automodule:: cutlass.cute.nvgpu
+   :members:
+   :undoc-members:
+   :show-inheritance:

media/docs/pythonDSL/cute_dsl_api/cute_nvgpu_cpasync.rst

@@ -0,0 +1,10 @@
+.. _cute_nvgpu_cpasync:
+
+cpasync submodule
+=================
+
+.. automodule:: cutlass.cute.nvgpu.cpasync
+   :members:
+   :undoc-members:
+   :show-inheritance:
+   :special-members: __init__

media/docs/pythonDSL/cute_dsl_api/cute_nvgpu_tcgen05.rst

@@ -0,0 +1,10 @@
+.. _cute_nvgpu_tcgen05:
+
+tcgen05 submodule
+=================
+
+.. automodule:: cutlass.cute.nvgpu.tcgen05
+   :members:
+   :undoc-members:
+   :show-inheritance:
+   :special-members: __init__

media/docs/pythonDSL/cute_dsl_api/cute_nvgpu_warp.rst

@@ -0,0 +1,10 @@
+.. _cute_nvgpu_warp:
+
+warp submodule
+==============
+
+.. automodule:: cutlass.cute.nvgpu.warp
+   :members:
+   :undoc-members:
+   :show-inheritance:
+   :special-members: __init__

media/docs/pythonDSL/cute_dsl_api/cute_nvgpu_warpgroup.rst

@@ -0,0 +1,10 @@
+.. _cute_nvgpu_warpgroup:
+
+warpgroup submodule
+===================
+
+.. automodule:: cutlass.cute.nvgpu.warpgroup
+   :members:
+   :undoc-members:
+   :show-inheritance:
+   :special-members: __init__

media/docs/pythonDSL/cute_dsl_api/utils.rst

@@ -0,0 +1,9 @@
+cutlass.utils
+=============
+
+.. automodule:: cutlass.utils
+   :members:
+   :undoc-members:
+   :show-inheritance:
+   :special-members: __init__
+   :private-members: