conftrace_

attention efficiency

5 papers

Explore in graph

Co-occurring keywords · papers mentioning both

transformer optimization (2) efficient computing (2) attention mechanism (2) multi-segment encoding (1) hopper gpu (1) low-precision arithmetic (1) fp8 quantization (1) gpu computation (1) large language model (1) context compression (1)

Papers

FAEDKV: Infinite-Window Fourier Transform for Unbiased KV Cache Compression EMNLP 2025 FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision NeurIPS 2024 Context Compression for Auto-regressive Transformers with Sentinel Tokens EMNLP 2023 LAIT: Efficient Multi-Segment Encoding in Transformers with Layer-Adjustable Interaction ACL 2023 On the Locality of Attention in Direct Speech Translation ACL 2022