# llama.cpp v0.13 adds extended DMA support for faster binary ops

> The open‑source llama.cpp library released a new version on Oct 13 2026 that expands DMA broadcasting for binary operations across multiple platforms.

Oossa · 2026-10-13 · https://oossa.com/en/llama-cpp-v0-13-adds-extended-dma-support-for-faster-binary-ops

The ggml‑org team published llama.cpp release b11580 on Oct 13 2026. The update adds extended scalar DMA (direct memory access) support for binary operations, including new kernels for repeat and complex data. It also cleans up non‑DMA paths and adds support for non‑contiguous strides. The changes affect CPU, CUDA, Vulkan and Hexagon NPU builds on Linux, Windows, macOS and Android. Developers can now run more efficient tensor calculations on devices ranging from Apple Silicon to Snapdragon chips.

## The facts

- Release version b11580 published Oct 13 2026
- Adds DMA broadcasting for binary ops on CPU, CUDA, Vulkan, Hexagon NPU

## Why it matters

Developers can run llama.cpp models faster on a wider range of hardware, reducing inference time for end‑users.

## Sources & references

1. [ggml-org/llama.cpp b11580](https://github.com/ggml-org/llama.cpp/releases/tag/b11580) – llama.cpp, 2026-10-13

Last updated: 2026-10-13
