PulseAugur
中
实时 08:11:51
English(EN) vLLM Semantic Router Releases d3-ultra: A 27B Open Multimodal Decision Model

vLLM Semantic Router 发布 d3-ultra,一个 27B 的多模态决策模型

vLLM Semantic Router 发布了 d3-ultra,一个拥有 270 亿参数的多模态决策模型。该模型旨在以概率而非生成文本的方式回答类型化问题,并且它会处理一次输入以回答所有查询。在内部基准测试中,它表现强劲,尤其是在文本任务方面,尽管在基于图像的边界框定位任务上略逊于其同类模型 d3-turbo。 AI

影响 该模型能够一次处理输入以获得多个概率性答案,这可能会简化 AI 应用中的路由和分类任务。

排序理由 知名实验室的新模型发布。[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 d3-ultra,一个 27B 的多模态决策模型

本文如何被排名

Signal score
47 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Significant
知名实验室的新模型发布。[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) · Asif Razzaq ·

    vLLM Semantic Router 发布 d3-ultra:一个 27B 的开放多模态决策模型

    <p>vLLM Semantic Router released d3-ultra, a 27B open-weight multimodal decision model. It reads text, images and video once, then returns probabilities for every answer, scoring 87.2 on the team’s SR-Text test.</p> <p>The post <a href="https://www.marktechpost.com/2026/10/26/vll…