CUTLASS 3.3.0 (#1167)

* Release 3.3.0

Adds support for mixed precision GEMMs On Hopper and Ampere
Adds support for < 16B aligned GEMMs on Hopper
Enhancements to EVT
Enhancements to Python interface
Enhancements to Sub-byte type handling in CuTe
Several other bug-fixes and performance improvements.

* minor doc update

pyproject.toml

@@ -0,0 +1,28 @@
+[build-system]
+requires = ["setuptools"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "cutlass"
+version = "3.3.0.0"
+description = "CUTLASS"
+readme = "README.md"
+requires-python = ">=3.8"
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: BSD License",
+    "Operating System :: OS Independent",
+]
+dependencies = [
+  "cuda-python>=11.8.0",
+  "networkx",
+  "numpy",
+  "pydot",
+  "rmm-cu12 ; python_version>='3.9'",
+  "scipy",
+  "treelib"
+]
+
+[project.urls]
+"Homepage" = "https://github.com/nvidia/cutlass"
+"Bug Tracker" = "https://github.com/nvidia/cutlass/issues"