English(EN) b11633: ggml-cpu : size set_rows conversion buffer for all threads (#30454)

llama.cpp b11633 更新 ggml-cpu 线程缓冲区处理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-14 15:31

llama.cpp 项目发布了 b11633 版本，其中包括对其 ggml-cpu 组件的更新。这些更改解决了 SET_ROWS 转换缓冲区在多个线程之间如何处理的问题，通过确保 SET_ROWS 以单个任务执行，并且每个线程使用自己的转换缓冲区，来防止线程写入超出分配的缓冲区。 AI

影响对 CPU 推理库的次要更新，改进了线程安全性和缓冲区管理。

排序理由这是项目特定组件的软件更新，不是新模型发布或重大的行业事件。

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

本文如何被排名

Signal score: 2 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是项目特定组件的软件更新，不是新模型发布或重大的行业事件。
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: 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: 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。

llama.cpp — Releases TIER_1 English(EN) · am17an · 2026-10-14 15:31

b11633: ggml-cpu : 为所有线程设置 size_rows 转换缓冲区 (#30454)

<ul> <li>ggml-cpu : size set_rows conversion buffer for all threads</li> </ul> <p>SET_ROWS is planned with n_tasks = 1, but every thread runs it and uses its own row of the F16 -> F32 conversion buffer, so threads > 0 wrote past the work buffer when the graph had another mu…