4 papers
CODA: Rewriting Transformer Blocks as GEMM-Epilogue Programs
Han Guo, Jack Zhang, Arjun Menon +4
Transformer training systems are built around dense linear algebra, yet a nontrivial fraction of end-to-end time is spent on surrounding memory-bound operators. Normalization, acti…
FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling
Ted Zadouri, Markus Hoehnerbach, Jay Shah +3
Attention, as a core layer of the ubiquitous Transformer architecture, is the bottleneck for large language models and long-context applications. While FlashAttention-3 optimized a…
fVDB: A Deep-Learning Framework for Sparse, Large-Scale, and High-Performance Spatial Intelligence
Francis Williams, Jiahui Huang, Jonathan Swartz +9
We present fVDB, a novel GPU-optimized framework for deep learning on large-scale 3D data. fVDB provides a complete set of differentiable primitives to build deep learning architec…
Generalized Neighborhood Attention: Multi-dimensional Sparse Attention at the Speed of Light
Ali Hassani, Fengzhe Zhou, Aditya Kane +13
Many sparse attention mechanisms such as Neighborhood Attention have typically failed to consistently deliver speedup over the self attention baseline. This is largely due to the l…