NVIDIA/cudnn-frontend v1.12.1

v1.12.1 release

on GitHub

This release builds on top of the 1.12.0 release.

Bug fix

• Fixes an issue where d=256 was marked not supported in Hopper

Minor Enhancements

• Addressed several comments from code review.
• Improved the cmake workflow. See PR 125

Benchmark Results

• Published results of using cuDNN backend for default torch.sdpa op in comparison to other backend. See Llama-3.2-1B-Training for reference.
• Published comparison results of sdpa() in comparison to other backends. See sdpa_benchmark_bf16_training