English(EN) b11439: ggml: refactor selective expert copying to user code (#29943)

llama.cpp b11439 重构专家复制，添加 DeepSeek2 测试

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-06 07:59

llama.cpp 项目已发布 b11439 版本，其中包括将选择性专家复制重构为用户代码。此次更新还纳入了将两个模型纳入选择性专家复制测试的测试，特别是使用 DeepSeek2 作为测试模型。该版本还改进了注释和空格修复。 AI

影响此次 llama.cpp 更新改进了其处理选择性专家复制和测试的基础设施，可能会提高 DeepSeek2 等模型的性能。

排序理由这是针对特定项目的软件更新，而非前沿模型发布或重大行业事件。

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: 3 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是针对特定项目的软件更新，而非前沿模型发布或重大行业事件。
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, model release; 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 · 2026-10-06 07:59

b11439: ggml: 将选择性专家复制重构为用户代码 (#29943)

<ul> <li> ggml: refactor selective expert copying to user code </li> <li> tests: enroll two models into selective expert copy test </li> <li> tests: use deepseek2 as test model </li> <li> improve comment in ggml-backend.h </li> </ul> Co-authored-by:…