llama.cpp b10311 修复 Qwen3-TTS 重复文本问题

AI 摘要

llama.cpp 发布 b10311 版本，修复了 Qwen3-TTS 生成时文本流重复输入的问题。该问题源于非流式预填充与流式覆盖层不匹配，导致模型在生成时重复读取文本。修复后，覆盖层改为与预填充匹配的单个 tts_pad 行。

正文节选

<details open> mtmd: stop feeding the text stream again during Qwen3-TTS generation (#26706) The reference implementation has two mutually exclusive prompt layouts. In non streaming mode the prefill carries the whole utterance text plus tts_eos summed with codec_pad, and the trailing text hidden collapses to a single tts_pad row. In streaming mode the prefill carries only the first text token and the trailing rows stream the rest of the text followed by tts_eos. The pipeline built the non str

发布时间：2026-08-07 23:44

抓取时间：2026-08-07 23:57

来源机构：ggml-org