# llama.cpp adds Vulkan multi-device support and Windows binaries

> The open‑source llama.cpp library v b11594, released Oct 13 2026, lets multiple GPUs share host memory and adds official Windows builds.

Oossa · 2026-10-13 · https://oossa.com/en/llama-cpp-adds-vulkan-multi-device-support-and-windows-binaries

The ggml‑org team released llama.cpp version b11594 on Oct 13 2026. The update adds Vulkan support for multiple devices to share GPU‑visible host memory. It also includes a clean Windows binary, fixes for null pointers, and minor cleanup. Pre‑built packages are provided for macOS, iOS, Linux (CPU and Vulkan) and now Windows.

## The facts

- Release tag: b11594
- New Vulkan feature: multiple devices can access GPU‑visible host memory; Windows binaries added

## Why it matters

Developers can now run llama.cpp models on several GPUs at once and on Windows PCs, expanding hardware options.

## Sources & references

1. [ggml-org/llama.cpp b11594](https://github.com/ggml-org/llama.cpp/releases/tag/b11594) – llama.cpp, 2026-10-13

Last updated: 2026-10-13