# llama.cpp release b11795 adds server param forwarding

> The open‑source llama.cpp library now forwards extra sampling parameters through its /v1/messages API and provides new binary builds for macOS, Linux and iOS.

Oossa · 2026-10-21 · https://oossa.com/en/llama-cpp-release-b11795-adds-server-param-forwarding

The ggml‑org team released llama.cpp version b11795. The update changes the server so that sampling parameters can be passed unchanged in the extra_params field of the /v1/messages endpoint. It also adds pre‑built binaries for macOS (Apple Silicon and Intel), iOS, and several Ubuntu CPU and Vulkan builds.

## The facts

- Release tag b11795 published on 2026‑10‑21
- New binaries for macOS arm64, macOS x64, iOS, Ubuntu x64, arm64, s390x and Vulkan

## Why it matters

Developers can now customize generation settings via the API without extra code, speeding up integration of llama.cpp into apps.

## Sources & references

1. [ggml-org/llama.cpp b11795](https://github.com/ggml-org/llama.cpp/releases/tag/b11795) – llama.cpp, 2026-10-21

Last updated: 2026-10-21