Skip to content
conftrace_

attention acceleration

2 papers

Explore in graph

Co-occurring keywords · papers mentioning both

dynamic token reduction (1) 8-bit quantization (1) bert inference (1) inference acceleration (1) reinforcement learning (1) transformer architecture (1) model compression (1)

Papers

SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration ICLR 2025 TR-BERT: Dynamic Token Reduction for Accelerating BERT Inference NAACL 2021