NVIDIA/cuEquivariance v0.11.0-rc3
NVIDIA/cuEquivariance
Captured source
source ↗0.11.0-rc3
Repository: NVIDIA/cuEquivariance
Tag: v0.11.0-rc3
Published: 2026-07-26T21:18:42Z
Prerelease: yes
Release notes: Release candidate for 0.11.0
What's new Triangle Attention: kv_lengths fast path Added a kv_lengths argument to triangle_attention, plus a mask_to_kv_lengths helper. Providing per-row key/value lengths routes variable-length (right-padded) inputs to the optimized fused attention kernel on Blackwell (SM100f), instead of the dense-mask path. kv_lengths and mask are mutually exclusive. Dense boolean masks are still supported; when a dense mask forces execution off the fast path, a warning is now emitted so callers can switch to kv_lengths for best performance. Attention Pair Bias New fused attention-with-pair-bias primitive with an optimized Blackwell (SM100f) implementation. Kernel / performance improvements Continued improvements to the Blackwell (SM100 / SM103) fused-attention kernels. Notes This is a release candidate intended for validation ahead of 0.11.0.