English(EN) Temperature 0, same model, two different GPUs: find the word that splits them, then pin it

LLM在不同GPU上的输出差异可追溯至浮点运算

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-08 21:32

即使设置和模型相同，LLM的输出也会因GPU之间浮点运算的差异而有所不同。这些差异源于浮点加法的非结合性，运算顺序的不同可能导致中间结果略有差异。虽然大多数token的生成置信度都很高，但在模型接近平局时，最后一位数字的微小差异就可能导致分歧，从而产生不同的token预测和后续输出。提供的脚本有助于识别模型运行之间发生此类分歧的确切token。 AI

影响凸显了LLM输出潜在的可复现性问题，影响研究和部署。

排序理由关于LLM因硬件差异导致可复现性问题的技术解释和脚本。[lever_c_demoted from research: ic=1 ai=1.0]

在 dev.to — LLM tag 阅读 →

基础设施

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 44 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于LLM因硬件差异导致可复现性问题的技术解释和脚本。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

dev.to — LLM tag TIER_1 English(EN) · Dekita · 2026-11-08 21:32

温度0，同一模型，两块不同GPU：找出分割它们的词，然后固定它

<p>You set the temperature to 0, you fix the seed, you run the same GGUF file, and the two GPUs disagree. One says 20. The other says 2000. Neither of them is wrong about its own arithmetic, and each one repeats itself exactly when you run it a second time. The difference is not …

本文如何被排名

报道来源 [1]

温度0，同一模型，两块不同GPU：找出分割它们的词，然后固定它

相关实体

相关话题