Pith. sign in

REVIEW 1 cited by

Identifying Sensitive Weights via Post-quantization Integral

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 2503.01901 v1 pith:WV7ECLOD submitted 2025-02-28 cs.LG cs.AI

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

Serving Large Language Models (LLMs) is costly. However, post-training weight quantization can address this problem by both compressing their sizes for limited memory and saving bandwidth for acceleration. As not all weight dimensions are equally important, those methods typically rely on a sensitivity metric, which indicates the element-wise influence of weights on loss function and is used to preprocess original weights for better quantization. In this work, we conduct an empirical study on the accuracy of the sensitivity metric, and find that existing gradient and Hessian based metrics are very inaccurate: they underestimate quantization's impact on the loss function by orders of magnitude, mainly due to the small convergence radius of local 2nd order approximation, \ie, gradient and Hessian term in Taylor's formula. To tackle this problem, we propose Post-quantization Integral (PQI), an accurate metric to estimate posterior sensitivity in a fine-grained manner. To leverage this accurate metric, we further propose ReQuant, a simple yet powerful framework that mainly consists of two Dense-and-Sparse detach components: self-adaptive outlier selection and step-wise significant weights detach. Results show that ReQuant boosts state-of-the-art post-training quantization methods, with a pronounced improvement of 2.66 perplexity gain on Llama 3.2 1B with QTIP.

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. SageAttention2++: A More Efficient Implementation of SageAttention2

    cs.LG 2025-05 conditional novelty 4.0 of 10

    Using the FP16-accumulator FP8 matmul instruction with narrowed quantization ranges for P and V yields up to 3.9x speedup over FlashAttention2 with negligible accuracy loss.

Pith tools