English(EN) b12065: kv-cache : never return 0 kv_rows for sequences without cells (#31570)

llama.cpp b12065 版本发布修复 kv-cache 重分配错误

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-03 05:51

llama.cpp 项目发布了 b12065 版本，该版本解决了其键值缓存 (key-value cache) 的一个问题。之前，没有单元格的序列可能导致缓存返回零行，从而使系统回退到密集 KQ 掩码。这种回退会导致后续更大的掩码因重分配错误而中止。 AI

影响对特定 AI 推理库的次要错误修复，不太可能对整个行业产生广泛影响。

排序理由这是一个特定项目的软件发布，而不是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: 9 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 这是一个特定项目的软件发布，而不是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: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

llama.cpp — Releases TIER_1 English(EN) · am17an · 2026-11-03 05:51

b12065: kv-cache : never return 0 kv_rows for sequences without cells (#31570)

<p>A cache that shares the cells of another one (f.ex. the gemma4 assistant) can build a graph before its sequences have any cells, f.ex. at the server warmup. get_n_kv_rows() then returned 0, which means that kv_rows are not used, so the graph fell back to the dense KQ mask and …