# llama.cpp b12052 adds OpenCL top-k masking

> The llama.cpp release adds topk_mask support to its OpenCL backend and offers downloadable builds for several platforms.

Oossa · 2026-11-02 · https://oossa.com/en/llama-cpp-b12052-adds-opencl-top-k-masking

The ggml-org team has released llama.cpp b12052, a new version of the software used to run language models. Its highlighted change is “add topk_mask” for OpenCL, a framework for running computation across different hardware. The release page also lists builds for macOS, iOS and several Linux systems.

## The facts

- Release: llama.cpp b12052.
- The release lists Linux builds for x64, arm64 and s390x.

## Why it matters

People running llama.cpp with OpenCL may be able to use top-k masking, though the release notes do not say which models or tasks benefit.

## Sources & references

1. [ggml-org/llama.cpp b12052](https://github.com/ggml-org/llama.cpp/releases/tag/b12052) – llama.cpp, 2026-11-02

Last updated: 2026-11-02