daniel/h3-blackwell-runtime
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
h3-blackwell-runtime/research/qkv_layout_variants
History
Daniel Maddern ea14b98544 Preserve Vortex performance research history
2026-08-25 20:30:22 +07:00
..
patches Preserve Vortex performance research history 2026-08-25 20:30:22 +07:00
README.md Preserve Vortex performance research history 2026-08-25 20:30:22 +07:00

README.md

QKV Layout, Swizzle, and Wide-Store Recovery

The recoverable source is split between the shared CUDA patch and a focused Python dispatch patch:

  • patches/0001-strided-nhd-dispatch.patch: current attention.py changes for projection-strided NHD Sage2 and contiguous token-major output.
  • ../shared_cuda_experimental_worktree/patches/0001-shared-cuda-experiments.patch: QKV split/layout kernels, vectorized 16-byte stores, generalized NVFP4 scale swizzle, and associated extension binding. This patch also contains other requested CUDA experiments and is not isolated.

No experimental dispatch or build default is added by this capsule.