V has a much flatter spectrum than K, so C1 selects full rank for almost every V head at 2 bpd; C2 and KL reordering add no measurable V-side gain, and V-only compression remains much worse than K-only below 3 bpd before approaching FP16 around 4–5 bpd.

V has a much flatter spectrum than K, so C1 selects full rank for almost every V head at 2 bpd; C2 and KL reordering add no measurable V-side gain, and V-only compression remains much worse than K-only below 3 bpd before approaching FP16 around 4–5 bpd. · CiteArk

测量结果

已评估 0/4 项

获得支持 0有争议或冲突 0尚未评估 4

保留同一结论下的完整结果组。已有评估排在前面；单项判断不替代整组结论。展开行查看条件、来源与历次证据。

每行是一项测量，分别显示论文报告、最近可用实测和累计证据状态。
指标与条件	论文报告	最近可用实测	证据判断
	0.46 ratio	—	尚未评估
side: V	128 dimensions	—	尚未评估
	4 bits per dimension	—	尚未评估
	5 bits per dimension	—	尚未评估

V has a much flatter spectrum than K, so C1 selects full rank for almost every V head at 2 bpd; C2 and KL reordering add no measurable V-side gain, and V-only compression remains much worse than K-only below 3 bpd before approaching FP16 around 4–5 bpd.

报告指标与观测值

Assessment（0）

关联运行（0）

测量结果