llama.cpp Release b9630 Adds cohere2moe Vocabulary for TINY_AYA Support
English summary
This release of llama.cpp adds the cohere2moe tokenizer to llama-vocab, enabling inference with the TINY_AYA model. The change was contributed via pull request #24601. Build artifacts are provided for macOS, Linux, Windows, and Android across various backends.
Chinese summary
本次 llama.cpp 发布将 cohere2moe 分词器添加到 llama-vocab 中，从而支持 TINY_AYA 模型的推理。该变动通过 PR #24601 贡献，同时提供了面向 macOS、Linux、Windows 和 Android 多个计算后端的构建产物。
Key points
llama.cpp now includes the cohere2moe vocabulary, adding tokenizer support for the TINY_AYA model.
llama.cpp 现已包含 cohere2moe 词汇表，为 TINY_AYA 模型添加分词器支持。
The change was implemented via pull request #24601 in the main repository.
该变动通过主仓库的拉取请求 #24601 实现。
Release b9630 ships pre-built binaries for desktop and mobile platforms with multiple acceleration backends.
b9630 版本附带适用于桌面和移动平台、多种加速后端的预编译二进制文件。