activity
20232026
most citedA 28nm 0.22μJ/token memory-compute-intensity-aware CNN-Transformer accelerator with hybrid-attention-based layer-fusion and cascaded pruning for semantic-segmentation

11 citations · 12 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2026

PQ-HSA: Reusing Product-Quantized Scores for Hybrid Sparse-Approximate Attention

Kunming Shao, Jierun Chen, Yanli Wang +4

At each decoding step a language model attends over the key-value (KV) cache of every earlier token, so at long context the attention call is bounded by memory bandwidth. Sparse at…