# llama.cpp adds Windows row‑prefetch support

> The open‑source llama.cpp library now prefetches model rows on Windows, improving inference speed on that platform.

Oossa · 2026-09-30 · https://oossa.com/en/llama-cpp-adds-windows-row-prefetch-support

The llama.cpp project released version b11294 on 30 September 2026. The update adds row‑prefetching for Windows, meaning the library can load model data in advance to speed up generation. The change was contributed by Pranesh Gonegandla and merged without further modification. It also includes minor clean‑up and build fixes.

## The facts

- Release date: 2026-09-30 ("Wed Sep 30 2026 20:14:41 GMT+0200")
- Feature: row prefetch on Windows

## Why it matters

Windows users of llama.cpp will see faster model inference thanks to the new prefetch logic.

## Sources & references

1. [ggml-org/llama.cpp b11294](https://github.com/ggml-org/llama.cpp/releases/tag/b11294) – llama.cpp, 2026-09-30

Last updated: 2026-09-30