NVIDIA/cudnn-frontend v1.17.0

v1.17.0-release

Repository: NVIDIA/cudnn-frontend

Tag: v1.17.0

Published: 2025-12-20T00:10:44Z

Prerelease: no

Release notes:

cuDNN Frontend v1.17.0 Release Notes

cuDNN Frontend v1.17.0 is the recommended version for cuDNN 9.17.0 and later releases.

New Features 🚀

Open-Source Kernels

• Native Sparse Attention : The Native Sparse Attention (NSA) module implements Native Sparse attention as described in the Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention. Samples of usage for Blackwell architecture in [test/python/fe_api/nsa](test/python/fe_api/nsa)

• Gemm/Swiglu : Gemm_Swiglu now supports block-scaled FP8/FP4 datatypes.

API changes:

• Output tensors have been renamed from "C" and "Glu" to "AB12" and "C", respectively.
• "use_2cta_intrs" Option has been removed. This will be inferred automatically from tile shape.

Enhancements ✨

Scaled Dot-Product Attention (SDPA)

• More samples: Open sourcing our sdpa [test harness](test/python/test_mhas_v2.py) and fp8 samples in [test/python/test_sdpa_fp8.py](test/python/test_sdpa_fp8.py)

Additional Improvements

• Tensor properties: Added vector Dim and vectorization count to the tensor properties.
• Graph wrapper: Fixed an issue in the native graph wrapper that caused BufferError in non-pytorch tensors.

Benchmarking 📊

• Updated the benchmark results for the sdpa improvements added in cuDNN 9.17.0. GB200 and GB300 data.

Samples

• cudnn Llama model : Added reference implementation of the [Llama model completely in cuDNN](samples/llama/).