From b18df7d206c53394bcdbd71dca917fed0842e684 Mon Sep 17 00:00:00 2001
From: Haicheng Wu <haichengw@nvidia.com>
Date: Mon, 15 Jun 2026 20:40:53 -0700
Subject: [PATCH] update to 4.4.3

---
 CHANGELOG.md                      | 5 +++++
 README.md                         | 4 ++--
 include/cutlass/version.h         | 2 +-
 python/cutlass_cppgen/__init__.py | 2 +-
 python/setup_cutlass.py           | 2 +-
 python/setup_library.py           | 2 +-
 python/setup_pycute.py            | 2 +-
 7 files changed, 12 insertions(+), 7 deletions(-)

diff --git a/CHANGELOG.md b/CHANGELOG.md
index 9bc51a129..bb3d291e7 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -2,6 +2,11 @@
 
 # CUTLASS 4.x
 
+## [4.4.3](https://github.com/NVIDIA/cutlass/releases/tag/v4.4.3) (2026-06-15)
+
+### CUTLASS C++
+* Make [version.h](https://github.com/NVIDIA/cutlass/blob/release/4.4/include/cutlass/version.h) NVRTC JIT compilation compatible.
+
 ## [4.4.2](https://github.com/NVIDIA/cutlass/releases/tag/v4.4.2) (2026-03-13)
 
 ### CuTe DSL
diff --git a/README.md b/README.md
index 122369cb5..439c594b9 100644
--- a/README.md
+++ b/README.md
@@ -1,9 +1,9 @@
 ![ALT](./media/images/gemm-hierarchy-with-epilogue-no-labels.png "Complete CUDA GEMM decomposition")
 # Overview
 
-# CUTLASS 4.4.2
+# CUTLASS 4.4.3
 
-_CUTLASS 4.4.2 - March 2026_
+_CUTLASS 4.4.3 - June 2026_
 
 CUTLASS is a collection of abstractions for implementing high-performance matrix-matrix multiplication (GEMM)
 and related computations at all levels and scales within CUDA. It incorporates strategies for
diff --git a/include/cutlass/version.h b/include/cutlass/version.h
index 0780fae25..960431532 100644
--- a/include/cutlass/version.h
+++ b/include/cutlass/version.h
@@ -40,7 +40,7 @@
 
 #define CUTLASS_MAJOR 4
 #define CUTLASS_MINOR 4
-#define CUTLASS_PATCH 2
+#define CUTLASS_PATCH 3
 
 #ifdef CUTLASS_VERSIONS_GENERATED
 #include "cutlass/version_extended.h"
diff --git a/python/cutlass_cppgen/__init__.py b/python/cutlass_cppgen/__init__.py
index 889b6f453..0364a47cd 100644
--- a/python/cutlass_cppgen/__init__.py
+++ b/python/cutlass_cppgen/__init__.py
@@ -133,7 +133,7 @@ def get_option_registry():
         this._option_registry = OptionRegistry(device_cc())
     return this._option_registry
 
-this.__version__ = '4.4.2'
+this.__version__ = '4.4.3'
 
 from cutlass_cppgen.backend import create_memory_pool
 from cutlass_cppgen.emit.pytorch import pytorch
diff --git a/python/setup_cutlass.py b/python/setup_cutlass.py
index 0d1abbb32..85fac9477 100644
--- a/python/setup_cutlass.py
+++ b/python/setup_cutlass.py
@@ -51,7 +51,7 @@ setup_pycute.perform_setup()
 
 setup(
     name='cutlass_cppgen',
-    version='4.4.2',
+    version='4.4.3',
     description='CUTLASS Pythonic Interface',
     package_dir={'': '.'},
     packages=[
diff --git a/python/setup_library.py b/python/setup_library.py
index 84edebc8c..0a8839bae 100644
--- a/python/setup_library.py
+++ b/python/setup_library.py
@@ -36,7 +36,7 @@ from setuptools import setup
 def perform_setup():
     setup(
         name='cutlass_library',
-        version='4.4.2',
+        version='4.4.3',
         description='CUTLASS library generation scripts',
         packages=['cutlass_library']
     )
diff --git a/python/setup_pycute.py b/python/setup_pycute.py
index c4ae36938..c888bcc4f 100644
--- a/python/setup_pycute.py
+++ b/python/setup_pycute.py
@@ -36,7 +36,7 @@ from setuptools import setup
 def perform_setup():
     setup(
         name='pycute',
-        version='4.4.2',
+        version='4.4.3',
         description='Python implementation of CuTe',
         packages=['pycute'],
     )