# llama.cpp version b11466 released with flash_attn fix and new binaries

> The ggml‑org project posted version b11466 on Oct 7 2026, adding a flash_attn bug fix and offering pre‑built binaries for macOS, iOS and several Linux setups.

Oossa · 2026-10-07 · https://oossa.com/en/llama-cpp-version-b11466-released-with-flash-attn-fix-and-new-binaries

ggml‑org released llama.cpp version b11466 on Oct 7 2026. The update fixes the flash_attn supports_op check for overlapping key‑value pairs. It also adds ready‑to‑run binaries for macOS Apple Silicon, macOS Intel, iOS, and multiple Ubuntu builds (CPU, Vulkan and CUDA 12.8). The files can be downloaded from the GitHub release page.

## The facts

- Version b11466 released on 2026-10-07.
- Binaries now cover macOS (Apple Silicon and Intel), iOS, and Ubuntu (CPU, Vulkan, CUDA 12.8).

## Why it matters

Developers can run the latest llama.cpp code on more platforms without building from source.

## Sources & references

1. [ggml-org/llama.cpp b11466](https://github.com/ggml-org/llama.cpp/releases/tag/b11466) – llama.cpp, 2026-10-07

Last updated: 2026-10-07