# llama.cpp adds optional ZDNN backend build

> The open‑source LLM runtime now can be compiled with IBM's ZDNN library, though tests are not included yet.

Oossa · 2026-09-30 · https://oossa.com/en/llama-cpp-adds-optional-zdnn-backend-build

The llama.cpp project added a build option for the ZDNN backend, a library that speeds up matrix math on IBM Z hardware. The change was committed by Aaron Teo on Sep 30 2026. The new code compiles the backend but does not run any tests yet.

## The facts

- Commit author: Aaron Teo (IBM)
- Release tag: b11269, published Sep 30 2026

## Why it matters

It lets developers try llama.cpp on IBM Z systems, potentially improving performance for large‑language‑model inference.

## Sources & references

1. [ggml-org/llama.cpp b11269](https://github.com/ggml-org/llama.cpp/releases/tag/b11269) – llama.cpp, 2026-09-30

Last updated: 2026-09-30