# llama.cpp releases new binary package b11640 with Vulkan workgroup fix

> The open‑source LLM runtime adds an L2‑friendly workgroup scheduling tweak and ships updated binaries for macOS, iOS and Ubuntu.

Oossa · 2026-10-15 · https://oossa.com/en/llama-cpp-releases-new-binary-package-b11640-with-vulkan-workgroup-fix

The ggml‑org team published llama.cpp version b11640. The update changes the Vulkan backend to use L2‑friendly workgroup scheduling for matrix multiplication. It also provides fresh pre‑built binaries for Apple Silicon, Intel Macs, iOS, and several Ubuntu builds (CPU, Vulkan and CUDA 12.8). Users can download the packages from the GitHub release page.

## The facts

- Version b11640 released on Thu Oct 15 2026
- Vulkan workgroup scheduling tweak (#30215) added

## Why it matters

The change can make LLaMA models run faster on GPUs that support Vulkan, helping developers on Linux and Android devices.

## Sources & references

1. [ggml-org/llama.cpp b11640](https://github.com/ggml-org/llama.cpp/releases/tag/b11640) – llama.cpp, 2026-10-15

Last updated: 2026-10-15