PulseAugur
中
实时 23:49:29
English(EN) What is Decision 3.0? vLLM Semantic Router’s New Open Decision Models

vLLM Semantic Router 发布 Decision 3.0 多模态决策模型

vLLM Semantic Router 发布了 Decision 3.0,这是一个新的五种开源多模态决策模型系列,参数量从 0.8B 到 27B 不等。这些模型可以处理文本、JSON 和图像来回答特定问题,返回概率而非生成的文本,这对于路由和护栏应用非常有用。这些模型基于 Qwen 基础模型进行微调,在内部评估中表现出竞争力,其中 9B 的 d3-flash 模型性能优于上一代的 27B 模型。延迟测量表明在 AMD Instinct MI325X GPU 上处理效率很高。 AI

影响 通过多模态输入的概率输出来为开发人员提供高效的路由和护栏功能。

排序理由 知名实验室发布新的开源多模态模型系列。[lever_c_demoted from frontier_release: ic=1 ai=1.0]

在 MarkTechPost 阅读 →

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

vLLM Semantic Router 发布 Decision 3.0 多模态决策模型

本文如何被排名

Signal score
46 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
知名实验室发布新的开源多模态模型系列。[lever_c_demoted from frontier_release: 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
model release, product
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]

  1. MarkTechPost TIER_1 English(EN) · Michal Sutter ·

    什么是 Decision 3.0?vLLM 语义路由器的全新开放决策模型

    <p>vLLM Semantic Router released Decision 3.0, 5 Apache-2.0 multimodal decision models from 0.8B to 27B. They answer choice, yes/no and score questions about text and images in one call, without generating text.</p> <p>The post <a href="https://www.marktechpost.com/2026/10/11/wha…