{
  "id": 9256666,
  "title": "Greedy Decoding Is Not Precision-Invariant: Cross-Precision Output Divergence in LLM Inference",
  "url": "https://urgent.news/2026/09/22/greedy-decoding-is-not-precision-invariant-cross-precision-output",
  "topic": "ai",
  "section": "AI",
  "published": "2026-09-22T15:54:16.000Z",
  "source": {
    "name": "arXiv cs.AI",
    "slug": "arxiv-cs-ai",
    "url": "https://arxiv.org/abs/2609.26621v1"
  },
  "original_language": "en",
  "account": null,
  "summary": "Greedy decoding from large language models is commonly treated as deterministic. We show it is not precision-invariant: the same model, prompt, and decoding algorithm produce different outputs in BF16 versus FP16 on identical hardware. Across our evaluations of six models (1.1B-7B parameters, four families; divergence additionally characterised at 12B) and three benchmarks, 49-100\\% of prompts…",
  "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."
}