TiledAttention is a cuTile-based SDPA kernel that balances performance with Python-level customizability for attention research in PyTorch.
NVIDIA Documentation, https://docs.nvidia.com/cuda/ tile-ir/latest/sections/introduction.html, accessed 2026-01-31
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
TiledAttention: a CUDA Tile SDPA Kernel for PyTorch
TiledAttention is a cuTile-based SDPA kernel that balances performance with Python-level customizability for attention research in PyTorch.