# llama.cpp b12124 adds OpenCL sigmoid support

> The new llama.cpp release supports non-contiguous sigmoid operations on OpenCL and offers download builds for several operating systems and processors.

Oossa · 2026-11-05 · https://oossa.com/en/llama-cpp-b12124-adds-opencl-sigmoid-support

The ggml-org team released llama.cpp version b12124 with a change to its OpenCL support: it can now handle sigmoid operations on non-contiguous data. OpenCL is a framework for running computing tasks on different processors.

The release page also lists prebuilt downloads for macOS, iOS and Ubuntu, including CPU and Vulkan builds. It does not describe broader performance changes or say which users will notice a difference.

## The facts

- Release: llama.cpp b12124, dated November 5, 2026.
- Listed downloads include macOS Apple Silicon and Intel builds, an iOS XCFramework, and Ubuntu CPU and Vulkan builds.

## Why it matters

Developers using llama.cpp with OpenCL can access the newly supported operation, but the release notes do not establish whether it improves speed or affects everyday users.

## Sources & references

1. [ggml-org/llama.cpp b12124](https://github.com/ggml-org/llama.cpp/releases/tag/b12124) – llama.cpp, 2026-11-05

Last updated: 2026-11-05