3.9.1 doc/version change (#2273)

CHANGELOG.md

@@ -1,5 +1,9 @@
 # NVIDIA CUTLASS Changelog
 
+## [3.9.1](https://github.com/NVIDIA/cutlass/releases/tag/v3.9.1) (2025-04-30)
+
+* Fixed Group Gemm hang issue in CUTLASS 3.x
+* Improved Hopper [Blockwise](./examples/67_hopper_fp8_warp_specialized_gemm_with_blockwise_scaling/67_hopper_fp8_warp_specialized_gemm_with_blockwise_scaling.cu) and [Groupwise](./examples/67_hopper_fp8_warp_specialized_gemm_with_blockwise_scaling/67_hopper_fp8_warp_specialized_gemm_with_groupwise_scaling.cu) GEMM performance.
 
 ## [3.9.0](https://github.com/NVIDIA/cutlass/releases/tag/v3.9.0) (2025-04-24)
 

README.md

@@ -1,8 +1,8 @@
 ![ALT](./media/images/gemm-hierarchy-with-epilogue-no-labels.png "Complete CUDA GEMM decomposition")
 
-# CUTLASS 3.9.0
+# CUTLASS 3.9.1
 
-_CUTLASS 3.9.0 - April 2025_
+_CUTLASS 3.9.1 - April 2025_
 
 CUTLASS is a collection of CUDA C++ template abstractions for implementing
 high-performance matrix-matrix multiplication (GEMM) and related computations at all levels 

include/cutlass/version.h

@@ -36,7 +36,7 @@
 
 #define CUTLASS_MAJOR 3
 #define CUTLASS_MINOR 9
-#define CUTLASS_PATCH 0
+#define CUTLASS_PATCH 1
 
 #ifdef CUTLASS_VERSIONS_GENERATED
 #include "cutlass/version_extended.h"

python/cutlass/__init__.py

@@ -133,7 +133,7 @@ def get_option_registry():
         this._option_registry = OptionRegistry(device_cc())
     return this._option_registry
 
-this.__version__ = '3.9.0'
+this.__version__ = '3.9.1'
 
 from cutlass.backend import create_memory_pool
 from cutlass.emit.pytorch import pytorch

python/setup_library.py

@@ -36,7 +36,7 @@ from setuptools import setup
 def perform_setup():
     setup(
         name='cutlass_library',
-        version='3.9.0',
+        version='3.9.1',
         description='CUTLASS library generation scripts',
         packages=['cutlass_library']
     )

python/setup_pycute.py

@@ -36,7 +36,7 @@ from setuptools import setup
 def perform_setup():
     setup(
         name='pycute',
-        version='3.9.0',
+        version='3.9.1',
         description='Python implementation of CuTe',
         packages=['pycute'],
     )