Is FlexRound superseded?

Q: Is FlexRound superseded?

FlexRound (LLM quantization): superseded — cited as a baseline and beaten by newer methods. 1 paper(s) critique it, 2 beat it on benchmarks — #23 of 80 most-superseded. Sub-problem: cluster led by FlexRound.

LLM quantization

FlexRound

FlexRound: Learnable Rounding based on Element-wise Division for Post-Training Quantization

Superseded baseline#23 of 80 most-superseded · first seen Jun 1, 2023

Superseded — cited as a baseline and beaten by newer methods

1 papers critique it · 2 beat it on benchmarks

What papers say

Verbatim critique sentences, each from a paper that cites FlexRound as a baseline.

FlexRound incurs considerable performance degradation on the massive multitask language understanding (MMLU) benchmark

— LRQ: Optimizing Post-Training Quantization for Large Language Models by Learning Low-Rank Weight-Scaling Matrices

Beaten on benchmarks

Head-to-head results where a newer method reports beating FlexRound. Values are copied from the source paper's tables — verify against the cited paper.

FlexRound+LFQ beats FlexRound
72.09 vs 70.24
IFEval (greedy) · [Llama 3.1 8B, W4, FlexRound]
LFQ: Logit-aware Final-block Quantization for Boosting the Generation Quality of Low-Bit Quantized LLMs