# llama.cpp release b11469 adds new MUSA kernel and binaries

> The ggml‑org/llama.cpp project released version b11469 on Oct 7, 2026, featuring a MUSA tile‑lightning indexer kernel and pre‑built binaries for macOS, iOS and Linux.

Oossa · 2026-10-07 · https://oossa.com/en/llama-cpp-release-b11469-adds-new-musa-kernel-and-binaries

ggml‑org released llama.cpp version b11469. The update adds a MUSA tile‑lightning indexer kernel, contributed by Xiaodong Ye. It also ships ready‑to‑run binaries for Apple Silicon, Intel Macs, iOS, and several Ubuntu builds (CPU, Vulkan and CUDA). Users can download the appropriate package from the GitHub release page.

## The facts

- Version b11469 released on 2026‑10‑07
- New MUSA kernel added (tile lightning indexer)

## Why it matters

Developers can now run llama.cpp locally on more hardware, including MUSA‑compatible GPUs, without building from source.

## Sources & references

1. [ggml-org/llama.cpp b11469](https://github.com/ggml-org/llama.cpp/releases/tag/b11469) – llama.cpp, 2026-10-07

Last updated: 2026-10-07