{
  "id": 10846322,
  "title": "STEPQuant: When and Where Errors Matter in Delta-Rule Recurrent State Quantization",
  "url": "https://urgent.news/2026/09/29/stepquant-when-and-where-errors-matter-in-delta-rule-recurrent-state",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-29T17:59:40.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.38169v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Linear attention replaces growing KV caches with fixed-size recurrent states, yet these persistent states can become a substantial memory bottleneck under concurrent serving. Directly quantizing recurrent states to low precision often leads to severe accuracy degradation, as quantization errors propagate through successive state updates. We discover that the impact of these errors depends on two…",
  "key_points": [],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}