cs.LGmath.NA

LampAttention: Look-Ahead Mixed-Precision FlashAttention for Dedicated Accelerators

📅 👥 8 authors arXiv:2609.39361v1

Authors

Abstract

While most attention logits can be computed in low precision without degrading numerical stability, current attention kernels fail to exploit this phenomenon. We introduce a novel hardware-algorithm co-design in the form of mixed-precision FlashAttention. Our method accumulates key-query products and evaluates their exponentials in 8-bit formats, then adaptively identifies sensitive sub-blocks and recomputes them in 16-bit formats. We propose the specifications for a dedicated accelerator capable of executing this pipeline efficiently. Simulated experiments with Qwen3 and Gemma 3 show that rerouting a selective minority of sub-blocks to high precision is sufficient to recover the baseline model performance.

Paper Information

arXiv ID:
2609.39361v1
Published:

Related Categories

cs.LGmath.NA