llama.cpp b12237：mtmd 支持 Gemma 4 音频输入流

AI 摘要

llama.cpp 发布 b12237 版本，其 mtmd（多模态）模块新增对 Gemma 4 输入音频流的支持，采用 480ms 步长处理音频。同时修复了 server 端实时嵌入逻辑：此前实时槽位强制开启 embeddings，导致带音频流的聊天模型（如 Gemma 4）在首批音频行上中止，现在仅对生成音频的模型保留 n_batch 输出。该版本同步提供 macOS、Linux、Windows、Android 等多平台预编译包。

正文节选

<details open> mtmd: support gemma 4 input audio stream (#31965) * mtmd: support gemma 4 input audio stream * use 480ms step * server: enable realtime embeddings only for audio generation The realtime slot forced embeddings on, which marks every row of a batch as an output. Only a model that generates audio reserves n_batch outputs, so a chat model with an audio stream (Gemma 4) aborted on its first batch of audio rows. The hidden state is only read by the audio generation pipeline. ------

发布时间：2026-11-10 07:43

抓取时间：2026-11-10 08:29

来源机构：ggml-org