Pith. sign in

REVIEW 1 cited by

SparseInfer: Training-free Prediction of Activation Sparsity for Fast LLM Inference

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2411.12692 v2 pith:RFJCGF4B submitted 2024-11-19 cs.PF

classification cs.PF
keywords sparsityactivationinferencepredictoraccuracyhoweverllmsoptimizing
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Leveraging sparsity is crucial for optimizing large language model inference. however, modern LLMs employing SiLU as their activation function exhibit minimal activation sparsity. Recent research has proposed replacing SiLU with ReLU to induce significant activation sparsity and showed no downstream task accuracy degradation through fine tuning. However, taking full advantage of it required training a predictor to estimate this sparsity. In this paper, we introduce SparseInfer, a simple, light weight, and training free predictor for activation sparsity of ReLU field LLMs, in which activation sparsity is predicted by comparing only the sign bits of inputs and weights. To compensate for possible prediction inaccuracy, an adaptive tuning of the predictor's conservativeness is enabled, which can also serve as a control knob for optimizing LLM inference. The proposed method achieves approximately faster inference speed over the state of the art, with negligible accuracy loss of within 1%p.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. A Sparsity Predicting Approach for Large Language Models via Activation Pattern Clustering

    cs.LG 2025-07 reject novelty 5.0 of 10

    A clustering method for LLM activation patterns achieves up to 79% centroid precision and a best perplexity of 12.49, but the reported perplexity assumes 100% accurate cluster selection and no predictor is built.

Pith tools