PulseAugur
实时 19:13:13

llama.cpp 发布新增模型支持、性能提升和安全修复 · 跟踪 4 个来源

llama.cpp 项目发布了多个更新,包括 b11003 版本,该版本增加了对 HrmTextForCausalLM 模型(采用双栈 Transformer 架构)的支持。此次发布还指出,大部分代码是在 GLM 5.3 的协助下由 AI 生成的。之前的版本 b11002b11001 专注于在各种平台和硬件加速器(如 CUDA 和 Vulkan)上的性能改进和错误修复。b11000 版本解决了与缓存计算图相关的关键安全漏洞,该漏洞可能导致远程代码执行。 AI

影响 这些更新提高了流行的开源推理引擎的性能和安全性,可能加速本地 LLM 的部署。

排序理由 该集群包含 llama.cpp 项目的多个发布说明,详细介绍了软件更新、错误修复和新功能实现,属于“工具”类别。

在 llama.cpp — Releases 阅读 →

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

llama.cpp 发布新增模型支持、性能提升和安全修复 · 跟踪 4 个来源

本文如何被排名

Signal score
6 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含 llama.cpp 项目的多个发布说明,详细介绍了软件更新、错误修复和新功能实现,属于“工具”类别。
Source corroboration
4 independent sources
Strong cross-source corroboration — multiple independent publishers covered this within the clustering window.
Topics
model release, infra, other
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
Same-day
Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准

报道来源 [4]

  1. llama.cpp — Releases TIER_1 (SO) · github-actions[bot] ·

    b11003

    <details open=""> <p>model : add support for HrmTextForCausalLM (DFM Mimir 1B) (<a class="issue-link js-issue-link" href="https://github.com/ggml-org/llama.cpp/pull/27625">#27625</a>)</p> <ul> <li>model : add support for HrmTextForCausalLM (DFM Mimir 1B)</li> </ul> <p>HRM-Text ru…

  2. llama.cpp — Releases TIER_1 (SO) · github-actions[bot] ·

    b11002

    <details open=""> <p>CUDA/HIP: improve access patterns in im2col (<a class="issue-link js-issue-link" href="https://github.com/ggml-org/llama.cpp/pull/28013">#28013</a>)</p> </details> <p><strong>Website:</strong></p> <ul> <li><a href="https://llama.app" rel="nofollow">https://ll…

  3. llama.cpp — Releases TIER_1 (SO) · github-actions[bot] ·

    b11001

    <details open=""> <p>spacemit : fix wrong transpose function for int16 data (<a class="issue-link js-issue-link" href="https://github.com/ggml-org/llama.cpp/pull/25161">#25161</a>)</p> <p>The <code>sizeof(int16_t)</code> branch in <code>permute_transpose_impl</code> calls<br /> <…

  4. llama.cpp — Releases TIER_1 (SO) · github-actions[bot] ·

    b11000

    <details open=""> <p>rpc : invalidate cached compute graph when a referenced buffer is freed (<a class="issue-link js-issue-link" href="https://github.com/ggml-org/llama.cpp/pull/24292">#24292</a>)</p> <p>The server caches the most recent compute graph per device so that<br /> GR…