pith. machine review for the scientific record. sign in

Kvsharer: Efficient inference via layer-wise dissimilar kv cache sharing

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 2

years

2026 2

verdicts

UNVERDICTED 2

roles

background 1

polarities

background 1

representative citing papers

Search Your Block Floating Point Scales!

cs.LG · 2026-05-12 · unverdicted · novelty 6.0

ScaleSearch optimizes block floating point scales via fine-grained search to cut quantization error by 27% for NVFP4, improving PTQ by up to 15 points on MATH500 for Qwen3-8B and attention PPL by 0.77 on Llama 3.1 70B.

KV Cache Offloading for Context-Intensive Tasks

cs.LG · 2026-04-09 · unverdicted · novelty 6.0 · 3 refs

KV offloading hurts accuracy on context-heavy tasks because of low-rank key projections and bad landmarks, but a simpler strategy improves results across models and benchmarks.

citing papers explorer

Showing 2 of 2 citing papers.

  • Search Your Block Floating Point Scales! cs.LG · 2026-05-12 · unverdicted · none · ref 165

    ScaleSearch optimizes block floating point scales via fine-grained search to cut quantization error by 27% for NVFP4, improving PTQ by up to 15 points on MATH500 for Qwen3-8B and attention PPL by 0.77 on Llama 3.1 70B.

  • KV Cache Offloading for Context-Intensive Tasks cs.LG · 2026-04-09 · unverdicted · none · ref 61 · 3 links

    KV offloading hurts accuracy on context-heavy tasks because of low-rank key projections and bad landmarks, but a simpler strategy improves results across models and benchmarks.