most citedProximu$: Efficiently Scaling DNN Inference in Multi-core CPUs through Near-Cache Compute

3 citations · 3 across the 4 of their papers we have counts for

collaborators
Showing cs.CLShow all

1 paper · 1 filter

cs.CL2024

QCQA: Quality and Capacity-aware grouped Query Attention

Vinay Joshi, Prashant Laddha, Shambhavi Sinha +2

Excessive memory requirements of key and value features (KV-cache) present significant challenges in the autoregressive inference of large language models (LLMs), restricting both…