# llama.cpp release b11715 adds AMD GPU support and new binaries

> The open‑source Llama inference library released version b11715 on Oct 17 2026, adding AMD GPU instructions and pre‑built binaries for macOS, iOS and Linux.

Oossa · 2026-10-17 · https://oossa.com/en/llama-cpp-release-b11715-adds-amd-gpu-support-and-new-binaries

The ggml‑org team published llama.cpp version b11715 on 2026‑10‑17. The update adds a HIP instruction (__builtin_amdgcn_perm) for AMD GPU unpacking, improving AMD GPU performance. It also ships pre‑compiled binaries for Apple Silicon, Intel macOS, iOS, and several Ubuntu configurations (CPU, Vulkan, CUDA 12.8). Users can download the appropriate package from the GitHub release page.

## The facts

- Release version: b11715
- Release date: 2026‑10‑17

## Why it matters

Developers can now run Llama models faster on AMD GPUs and get ready‑to‑run binaries for more platforms without building from source.

## Sources & references

1. [ggml-org/llama.cpp b11715](https://github.com/ggml-org/llama.cpp/releases/tag/b11715) – llama.cpp, 2026-10-17

Last updated: 2026-10-17