# llama.cpp release b11769 fixes router disconnect handling

> The open‑source llama.cpp library version b11769 updates server routing to cancel requests promptly and adds new binary builds for macOS, Linux and iOS.

Oossa · 2026-10-21 · https://oossa.com/en/llama-cpp-release-b11769-fixes-router-disconnect-handling

The ggml‑org team released llama.cpp version b11769. The update fixes a bug where the server router did not fully pass client disconnect signals to child processes, which could delay request cancellation. The change also removes a timing‑sensitive test. New pre‑built binaries are now available for macOS Apple Silicon, macOS Intel, iOS, and several Ubuntu variants.

## The facts

- Release version b11769 published on 2026-10-21
- Includes binaries for macOS arm64, macOS x64, iOS, Ubuntu x64, arm64, s390x and Vulkan

## Why it matters

Developers can run llama.cpp locally with more reliable request cancellation, reducing wasted compute on interrupted tasks.

## Sources & references

1. [ggml-org/llama.cpp b11769](https://github.com/ggml-org/llama.cpp/releases/tag/b11769) – llama.cpp, 2026-10-21

Last updated: 2026-10-21