# llama.cpp adds fused SYCL alpha gate and new binaries

> The open‑source llama.cpp library updates SYCL support and releases pre‑built binaries for macOS, iOS and Ubuntu.

Oossa · 2026-10-08 · https://oossa.com/en/llama-cpp-adds-fused-sycl-alpha-gate-and-new-binaries

The llama.cpp project released version b11497 on Oct 8, 2026. It adds a SYCL optimization that fuses add, unary and multiply operations in the delta‑net alpha gate. The update also adds test coverage for this fused chain. Pre‑built binaries for macOS (Apple Silicon and Intel), iOS, and several Ubuntu builds (CPU and Vulkan) are now available for download.

## The facts

- Version b11497 released on 2026-10-08
- Binaries provided for macOS arm64, macOS x64, iOS, Ubuntu x64/arm64/s390x (CPU and Vulkan)

## Why it matters

Developers can run llama.cpp faster on more hardware without building from source.

## Sources & references

1. [ggml-org/llama.cpp b11497](https://github.com/ggml-org/llama.cpp/releases/tag/b11497) – llama.cpp, 2026-10-08

Last updated: 2026-10-08