pith. sign in

Accurate and efficient singular value decomposition for LLMs via decay-aware rank allocation and feature-preserved weight update

1 Pith paper cite this work. Polarity classification is still indexing.

1 Pith paper citing it

citation-role summary

background 1

citation-polarity summary

fields

cs.LG 1

years

2026 1

verdicts

UNVERDICTED 1

roles

background 1

polarities

background 1

representative citing papers

FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast

cs.LG · 2026-05-08 · unverdicted · novelty 6.0

FlashSVD v1.5 delivers up to 2.55x faster autoregressive decode and 2.39x end-to-end speedup for SVD-compressed transformers by reorganizing execution paths with dense-KV decode, packed MLP kernels, and per-layer CUDA graphs.

citing papers explorer

Showing 1 of 1 citing paper.

  • FlashSVD v1.5: Making Low-Rank Transformers Inference Actually Fast cs.LG · 2026-05-08 · unverdicted · none · ref 3

    FlashSVD v1.5 delivers up to 2.55x faster autoregressive decode and 2.39x end-to-end speedup for SVD-compressed transformers by reorganizing execution paths with dense-KV decode, packed MLP kernels, and per-layer CUDA graphs.