Tag

#routing

2 stories tagged routing.

Horizontal bar chart comparing three AUC scores for MoE route flips: flip detection at 0.772, harm prediction given a flip at 0.490, and benefit prediction at 0.499. The last two are at chance level. Source: arXiv 2608.11212.

Detecting MoE route flips works, fixing them is near-random

MoE route flips are tokens that switch experts under KV-cache quantization. Detection hits AUC 0.772 but harm prediction is at chance, bounding selective repair.

Lars Cornelissen · Aug 14, 2026

Donut chart showing that on fragile tokens, the standard MoE route is the best option on only 0.8 percent of tokens while a better alternative exists on 99.2 percent. Quantized MoE route flips concentrate damage on these fragile tokens.

Engineering

Quantized MoE route flips: easy to detect, hard to fix

Quantized MoE route flips silently corrupt expert selection. Detection is easy, but knowing whether to fix each flip requires causal damage analysis.

Lars Cornelissen · Aug 13, 2026