tool · first seen 20 Oct 2026
FlexAttention
A PyTorch API for expressing custom attention variants such as score modification and masking compiled into fused kernels.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Efficient Edge-aware Attention Network for Graph GenerationPapers · 20 Oct 2026 · Vincent Jung, Alba Carballo-Castro, Yiming Qin, Lonneke van der Plas, Pascal Fro…
- Causal Attention on CPU: A Cache-Aware and Load-Balanced Scheduling Kernel for PrefillPapers · 28 Oct 2026 · Kwun Fung Lau, Frost Mitchell, Kanya Mo, Emani Ashok
Latest sources
- Causal Attention on CPU: A Cache-Aware and Load-Balanced Scheduling Kernel for PrefillPapers · 28 Oct 2026 · Kwun Fung Lau, Frost Mitchell, Kanya Mo, Emani Ashok
- Efficient Edge-aware Attention Network for Graph GenerationPapers · 20 Oct 2026 · Vincent Jung, Alba Carballo-Castro, Yiming Qin, Lonneke van der Plas, Pascal Fro…