Flashlight is a compiler-native PyTorch framework that generates efficient fused kernels for arbitrary and data-dependent attention variants, supporting more cases than FlexAttention with competitive performance.
Flexattention: The flexibility of pytorch with the performance of flashattention, Aug 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Flashlight: PyTorch Compiler Extensions to Accelerate Attention Variants
Flashlight is a compiler-native PyTorch framework that generates efficient fused kernels for arbitrary and data-dependent attention variants, supporting more cases than FlexAttention with competitive performance.