Skip to content

Pre-Alpha Release

Pre-release
Pre-release

Choose a tag to compare

View all tags
@vhrabar vhrabar released this 29 Jun 14:43
v0.1.0
5ff3582
This commit was signed with the committer’s verified signature.
vhrabar Vedran Hrabar
GPG key ID: 6BC1D8B249221EF3
Verified
Learn about vigilant mode.

Morphottention v0.1.0

First public release: Mathematical Morphology-based self-attention for PyTorch, built around a Flash-style fused CUDA kernel

Pre-Alpha. The forward pass is implemented and usable for inference; the backward pass has not yetbeen implemented.

Highlights

  • Fused forward kernel : morphological hypercube attention computed in a single Flash-style streaming pass (online softmax, no materialized score matrix).
  • MorphoAttention nn.Module : drop-in attention layer with learnable projection, per-head gates, and value projection.
  • Functional & autograd API : morpho_attention(...) and MorphoAttentionFunction for lower-level use.
  • GPU support : kernels compiled for sm_90, sm_100, and sm_120 (Hopper / Blackwell).
Assets 6
Loading