PulseAugur
中
实时 11:59:35
English(EN) We wrote up a comprehensive guide on using Kimi K3

Moonshot AI 发布 Kimi K3,一个 2.8T 参数的开源模型

Moonshot AI 发布了 Kimi K3,这是一款拥有 2.8 万亿参数和 100 万 token 上下文窗口的新旗舰模型。这款开源模型代表了规模上的重大成就,其效率比前代 Kimi K2 提高了 2.5 倍。技术报告详细介绍了 Kimi K3 的创新架构,包括 Kimi Delta Attention (KDA) 和 Gated MLA with No Position Encoding (NoPE),这些技术实现了其令人印象深刻的规模和长上下文能力。 AI

影响 为开源模型的规模和效率树立了新的标杆,有望加速长上下文窗口模型的研究和开发。

排序理由 前沿实验室模型发布,附有技术报告和开源可用性。[lever_c_demoted from frontier_release: ic=2 ai=1.0]

在 X — Together (inference / OSS) 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →

Moonshot AI 发布 Kimi K3,一个 2.8T 参数的开源模型

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
Significant
前沿实验室模型发布,附有技术报告和开源可用性。[lever_c_demoted from frontier_release: ic=2 ai=1.0]
Source corroboration
2 independent sources
Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics
model release, 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
72 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [2]

  1. X — Together (inference / OSS) TIER_1 English(EN) · togethercompute ·

    我们撰写了关于使用 Kimi K3 的综合指南

    We wrote up a comprehensive guide on using Kimi K3 Read it here 👇

  2. Towards AI TIER_1 English(EN) · Mengliu Zhao ·

    Kimi K3 技术报告内幕

    <h4>The success of linear attention and the new era of scaling</h4><p>Kimi-series latest model, K3, got scaled up to 2.8 trillion parameters. <em>Impressive.</em></p><p>Moonshot AI’s <a href="https://arxiv.org/pdf/2607.24653">Kimi K3 technical report</a> opens with a model that i…