# llama.cpp b12029 fixes an InternVL token-order bug

> The ggml-org release fixes how llama.cpp handles InternVL’s CLS token and includes downloads for several platforms.

Oossa · 2026-11-01 · https://oossa.com/en/llama-cpp-b12029-fixes-an-internvl-token-order-bug

ggml-org has released llama.cpp b12029, a new version of its software for running language models. The release notes list one change: a fix to the order of InternVL’s CLS token, a special token used when processing multimodal input. Downloads are listed for macOS, iOS and several Linux configurations, including CPU and Vulkan builds. The release notes do not explain which users or tasks are affected by the fix.

## The facts

- The release is named llama.cpp b12029.
- The listed change is “fix InternVL CLS token order” (#30886).

## Why it matters

People running InternVL through llama.cpp may benefit from the token-order fix, but the release notes do not specify its practical effect or scope.

## Sources & references

1. [ggml-org/llama.cpp b12029](https://github.com/ggml-org/llama.cpp/releases/tag/b12029) – llama.cpp, 2026-11-01

Last updated: 2026-11-01