llama.cpp b11619：移除嵌入图冗余的 t_embd 扩展

AI 摘要

llama.cpp 发布 b11619 版本，主要变更是从嵌入图中移除 t_embd 扩展操作（#30461）。由于这些图仅用于生成嵌入，且 build_pooling() 已为每种池化类型扩展输出，模型图末尾的扩展属于冗余。该版本同时提供 macOS、Linux、Windows、Android 等多平台预编译包。

正文节选

<details open> models: drop the t_embd expand of the embedding graphs (#30461) These graphs only produce embeddings, and build_pooling() already expands its output for every pooling type, so the expand at the end of the model graph is redundant. </details> **Website:** - <https://llama.app> **Attestations:** - <https://github.com/ggml-org/llama.cpp/attestations/55957395> **macOS/iOS:** - [macOS Apple Silicon (arm64)](https://github.com/ggml-org/llama.cpp/releases/download/b11619/llama-b116

发布时间：2026-10-15 02:28

抓取时间：2026-10-15 02:54

来源机构：ggml-org