PulseAugur
中
实时 21:25:09

Ollama v0.40.9 增加了语音生成、决策模型和跨平台支持

Ollama 发布了 v0.40.9 版本,引入了多项新功能和改进。此次更新支持使用 Phonon 在 Apple Silicon 上进行语音生成,允许用户朗读文本或模型回复,并通过兼容 OpenAI 的端点流式传输音频。此外,Ollama 现在支持 vLLM Semantic Router 的决策模型,能够根据文本、结构化状态或图像对选项进行分类、是/否回答和评分。该版本还将 Flint 引入 Linux 和 Windows,并进行了其他增强,例如改进了流式请求错误报告和对编码工具更好的上下文长度处理。 AI

影响 通过语音和决策能力等新功能增强了本地 LLM 的可用性。

排序理由 这是用于本地运行 LLM 的工具的软件发布,不是前沿模型发布或重大的行业事件。

在 Medium — Claude tag 阅读 →

AI 生成摘要 · Google Gemini · 来自 4 个来源。 我们如何撰写摘要 →

Ollama v0.40.9 增加了语音生成、决策模型和跨平台支持

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
这是用于本地运行 LLM 的工具的软件发布,不是前沿模型发布或重大的行业事件。
Source corroboration
4 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
product, 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
32 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.
Coverage growth since scoring
+1 source(s) since last score
New sources have picked up this story since our last re-score. Score will update on the next scoring pass.

完整方法见我们的编辑标准。

报道来源 [4]

  1. Ollama — Releases TIER_1 (SK) · github-actions[bot] ·

    v0.40.9

    <h2>Speech</h2> <p>Ollama can now generate <a href="https://docs.ollama.com/capabilities/speech" rel="nofollow">speech</a> with Phonon on Apple Silicon. <code>ollama run</code> plays text or a chat model's reply aloud as the audio is generated, and apps can stream audio through t…

  2. Ollama — Releases TIER_1 (SK) · github-actions[bot] ·

    v0.40.9

    <h2>What's Changed</h2> <ul> <li>llama.cpp update</li> </ul> <p><strong>Full Changelog</strong>: <a class="commit-link" href="https://github.com/ollama/ollama/compare/v0.40.8...v0.40.9-rc0"><tt>v0.40.8...v0.40.9-rc0</tt></a></p>

  3. arXiv cs.LG TIER_1 English(EN) · Keshigeyan Chandrasegaran, Yue Zhao, Armin W. Thomas, Ehsan Adeli, Jiajun Wu, Juan Carlos Niebles, Li Fei-Fei, Michael Poli ·

    无需语言预训练的文本到图像生成模型

    arXiv:2610.26863v2 Announce Type: replace Abstract: Modern text-to-image (T2I) systems use internet-scale language pretraining for text-conditioned image generation. We ask whether language pretraining is necessary for strong T2I generation. We introduce Halcyon, a family of earl…

  4. Medium — Claude tag TIER_1 Español(ES) · Oscar ·

    Lucid Coding

    <div class="medium-feed-item"><p class="medium-feed-snippet">I&#x2019;ve spent a year building software with AI coding agents every single day.</p><p class="medium-feed-link"><a href="https://opcastil1.medium.com/vibe-coding-awake-the-lucid-coding-manifesto-47adb6c2af13?source=rs…