leavelet/cutlass
1
0
Fork 0
Code Issues Pull Requests Actions 27 Packages Projects Releases Wiki Activity

v4.3.5 update. (#2934)

Browse Source 
* v4.3.5 update.

* Update copyright to 2026
This commit is contained in:
Junkai-Wu
2026-01-08 15:02:56 -05:00
committed by GitHub
parent f86feb0aa8
commit 0d2b201e8c
2788 changed files with 3172 additions and 3071 deletions
Download Patch File Download Diff File Expand all files Collapse all files
media/docs/cpp/blackwell_cluster_launch_control.md
+1 -1
View File
@@ -122,7 +122,7 @@ The CLC pipeline has a depth of 3 to overlap the CLC operations of multiple wave
### Copyright
Copyright (c) 2025 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2025 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/blackwell_functionality.md
+1 -1
View File
@@ -725,7 +725,7 @@ Specialized policies must be used to generate mixed-input-datatype `mx_float4_t`
### Copyright
Copyright (c) 2025 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2025 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/build/building_in_windows_with_visual_studio.md
+1 -1
View File
@@ -88,7 +88,7 @@ As a result, one will need to know when to rerun CMake by hand.
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/build/building_with_clang_as_host_compiler.md
+1 -1
View File
@@ -57,7 +57,7 @@ then one can set `CMAKE_CUDA_COMPILER` as follows.
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/code_organization.md
+1 -1
View File
@@ -236,7 +236,7 @@ of tests run may vary over time as more are added.
# Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/cute/00_quickstart.md
+1 -1
View File
@@ -120,7 +120,7 @@ The `cute::print_latex` function will print LaTeX commands that you can use to b
## Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/cute/01_layout.md
+1 -1
View File
@@ -538,7 +538,7 @@ a multidimensional `mdspan` does not accept 1-D coordinates.
## Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/cute/02_layout_algebra.md
+1 -1
View File
@@ -583,7 +583,7 @@ flat_product : (M, N, TileM, TileN, L, ...)
## Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/cute/03_tensor.md
+1 -1
View File
@@ -390,7 +390,7 @@ This applies a statically shaped `Tiler` to the global memory `Tensor`, creates
## Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/cute/04_algorithms.md
+1 -1
View File
@@ -224,7 +224,7 @@ directory.
## Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/cute/0t_mma_atom.md
+1 -1
View File
@@ -510,7 +510,7 @@ To see how these `TiledMMA`s are used to partition data tensors, see the [`0x_ge
## Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/cute/0x_gemm_tutorial.md
+1 -1
View File
@@ -533,7 +533,7 @@ Similar examples can be found for CUTLASS 3.x kernels that are based on CuTe, su
## Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/cute/0z_tma_tensors.md
+1 -1
View File
@@ -236,7 +236,7 @@ ArithTuple(0,0) o (4,5):(_1@1,_1@0):
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/cutlass_3x_backwards_compatibility.md
+1 -1
View File
@@ -440,7 +440,7 @@ as the mappings are not always bijective.
### Copyright
Copyright (c) 2023 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2023 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/cutlass_3x_design.md
+1 -1
View File
@@ -116,7 +116,7 @@ If the code compiles, it's probably correct.
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/dependent_kernel_launch.md
+1 -1
View File
@@ -43,7 +43,7 @@ problem sizes. For more information, we refer the reader to [the example](https:
## Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/doxygen_mainpage.md
+1 -1
View File
@@ -38,7 +38,7 @@ has a variety of examples.
# Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/efficient_gemm.md
+1 -1
View File
@@ -259,7 +259,7 @@ targeting NVIDIA GPUs.
# Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/functionality.md
+1 -1
View File
@@ -279,7 +279,7 @@ CUDA exposes warp-level matrix operations in the CUDA C++ WMMA API. The CUDA C++
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/fundamental_types.md
+1 -1
View File
@@ -357,7 +357,7 @@ support on current and future NVIDIA GPUs.
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/gemm_api.md
+1 -1
View File
@@ -540,7 +540,7 @@ to inline PTX.
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/gemm_api_3x.md
+1 -1
View File
@@ -672,7 +672,7 @@ please refer to CuTe's tutorial, e.g., the sections on
### Copyright
Copyright (c) 2023 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2023 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/grouped_scheduler.md
+1 -1
View File
@@ -387,7 +387,7 @@ and without sorting to see whether it helps in your case.
## Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/ide_setup.md
+1 -1
View File
@@ -120,7 +120,7 @@ clang doesn't understand many of the compiler flags used by nvcc. Hence, for now
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/implicit_gemm_convolution.md
+1 -1
View File
@@ -759,7 +759,7 @@ Convolution can also be run by the CUTLASS Profiler.
# Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/layout.md
+1 -1
View File
@@ -270,7 +270,7 @@ Permuted Shared Memory Layouts:
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/pipeline.md
+1 -1
View File
@@ -179,7 +179,7 @@ for more details.
# Copyright
Copyright (c) 2023 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2023 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/profiler.md
+1 -1
View File
@@ -784,7 +784,7 @@ reference_device: Passed
# Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/programming_guidelines.md
+1 -1
View File
@@ -1159,7 +1159,7 @@ However, A is certainly M major if interpreted as a matrix.
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/quickstart.md
+1 -1
View File
@@ -752,7 +752,7 @@ We encourage a user to refer to Sm100 unit tests and the generated profiler-base
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/terminology.md
+1 -1
View File
@@ -83,7 +83,7 @@ replaced by [MMA and Copy atoms from CuTe](cute/0t_mma_atom.md).
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/tile_iterator_concept.md
+1 -1
View File
@@ -471,7 +471,7 @@ struct WriteableReadableRandomAccessContiguousTileIteratorConcept {
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```
media/docs/cpp/utilities.md
+1 -1
View File
@@ -433,7 +433,7 @@ Please note that `synclog` is an experimental feature, and its functionality is
### Copyright
Copyright (c) 2017 - 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
Copyright (c) 2017 - 2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
SPDX-License-Identifier: BSD-3-Clause
```