Skip to content

Add acknowledgements for cuteDSL Kernels #305

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
Anerudhan merged 1 commit into from
Jun 11, 2026
Merged

Add acknowledgements for cuteDSL Kernels #305

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
42 changes: 42 additions & 0 deletions ACKNOWLEDGEMENTS.md
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,42 @@
# Acknowledgements

## CuTe DSL OSS kernels

Several open-source kernels in this repository originated in NVIDIA's CuTe DSL kernel
library. We gratefully acknowledge the contributors who helped develop, bring up,
and test these kernels.

Contributors include:

- Rachit Garg <rachitg@nvidia.com>
- Jack Yang <jackyang@nvidia.com>
- Hao Sheng <hsheng@nvidia.com>
- Alex Li <alel@nvidia.com>
- Aragorn Guan <aragorng@nvidia.com>
- Bangyu Shen <bangyus@nvidia.com>
- Caleb Du <cadu@nvidia.com>
- Xiao Song <xiaos@nvidia.com>
- Siddhartha Raman <sraman@nvidia.com>

This acknowledgement covers the CuTe DSL kernel work now represented by these
modules in `python/cudnn/`:

- `gemm_amax`
- `gemm_dsrelu`
- `gemm_srelu`
- `gemm_swiglu`
- `grouped_gemm/grouped_gemm_dglu`
- `grouped_gemm/grouped_gemm_dsrelu`
- `grouped_gemm/grouped_gemm_dswiglu`
- `grouped_gemm/grouped_gemm_glu`
- `grouped_gemm/grouped_gemm_glu_hadamard`
- `grouped_gemm/grouped_gemm_quant`
- `grouped_gemm/grouped_gemm_srelu`
- `grouped_gemm/grouped_gemm_swiglu`
- `grouped_gemm/grouped_gemm_wgrad`
- `discrete_grouped_gemm/discrete_grouped_gemm_dswiglu`
- `discrete_grouped_gemm/discrete_grouped_gemm_swiglu`
- `rmsnorm_rht_amax`

Thank you also to the broader CUTLASS/CuTe DSL and infrastructure teams who
supported the original kernel development.
2 changes: 2 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,6 +42,8 @@ We are now shipping **OSS kernels**, allowing you to inspect, modify, and contri
* **[SDPA PyTorch Op](https://github.com/NVIDIA/cudnn-frontend/tree/main/python/cudnn/experimental/ops):** PyTorch custom operator for cuDNN-accelerated Scaled Dot-Product Attention with autograd and `torch.compile` support.
* **[DSA](https://github.com/NVIDIA/cudnn-frontend/tree/main/python/cudnn/deepseek_sparse_attention):** DSA/CSA kernels for DSv4 and DSv3.2 for fprop and bprop.

Contributor credits for these OSS CuTe DSL kernels are listed in [Acknowledgements](ACKNOWLEDGEMENTS.md).

## Tech talks

* See our latest talk on GPU-Mode
Expand Down