English(EN) b12300: llama : remove non-fused GDN and ubatch-dependent graph nodes (#32078)

llama.cpp 发布 b12300 版本，进行图节点优化

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-11 13:16

llama.cpp 项目已发布 b12300 版本，包含多项优化和特定图节点的移除。值得注意的是，该版本移除了非融合 GDN 和 ubatch 依赖的图节点，并确保 graph_max_nodes 不再依赖于 ubatch 大小。这些更改旨在简化构建过程并可能提高性能。 AI

影响对特定 AI 项目的次要基础设施更新，不太可能产生广泛的行业影响。

排序理由这是特定项目的软件发布，而非前沿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: 4 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是特定项目的软件发布，而非前沿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) · ggerganov · 2026-11-11 13:16

b12300: llama : 移除非融合GDN和ubatch依赖图节点 (#32078)

<ul> <li>remove build_delta_net_chunking and build_delta_net_autoregressive</li> <li>always use the fused gated delta net</li> <li>make graph_max_nodes independent of the ubatch size</li> <li>drop the fused GDN probes and fused node tags</li> </ul> <p>Assisted-by: dsh:llama.cpp/g…