Aryan Kumar
2ac6336b57
The H3 dense self-attention call always ran on FlashAttention. On GB200, cuDNN's fused SDPA engine is a few percent faster in-model at 37k-109k tokens, but the ATen op has no shape metadata: it always reads inputs as [B, H, S, D], so handing it contiguous [B, S, H, D] is silently misread. Add FASTVIDEO_MINIMAX_H3_DENSE_ATTN=flash|cudnn (default flash) and route the dense, unmasked, inference-only call through a helper that presents BHSD strided views. Training calls, compiled regions, head sizes >128, non-contiguous inputs, VSA blocks and NVFP4 stay on their existing paths. FA4_* tuning and the default behaviour are unchanged.
FastVideo documentation
Canonical guides live in this directory. The Blume application in docs-site builds and publishes them at haoailab.com/FastVideo.
See Documenting FastVideo for local setup,
source ownership, page structure, validation, and deployment. The existing
GitHub Pages workflow publishes Blume from main with the same domain and base
path. MkDocs is no longer part of the build.
Cookbook sources
Recipe metadata, shared JavaScript, and tests remain under docs/. From the
repository root:
npm ci --prefix docs
npm run build:catalog --prefix docs
npm run check:cookbook --prefix docs
npm run test:cookbook --prefix docs
python -m unittest discover -s docs/tests -p 'test_*.py'
The combined browser bundle, notices, index and catalogs are generated together
under assets/cookbook-config/. Do not hand-edit or commit those outputs.
The site preparation builds and copies them into Blume's public assets.
See the recipe authoring guide and
configuration API contract before changing the schema.
The capacity estimation guide covers reusable
hardware/component catalogs and optional recorded inference runs in existing
model manifests.