# llama.cpp release b11555 adds CPU fix and new binaries

> The open‑source Llama inference library updates to b11555, fixing AVX2 CPUs that missed F16C support and publishing fresh builds for macOS, iOS and Linux.

Oossa · 2026-10-11 · https://oossa.com/en/llama-cpp-release-b11555-adds-cpu-fix-and-new-binaries

ggml‑org released llama.cpp version b11555. The update corrects a bug where AVX2 CPUs did not use the F16C instruction set even when it was available. The release also ships new binary packages for macOS Apple Silicon, macOS Intel, iOS, and several Ubuntu configurations including Vulkan and CUDA 12.8 support.

## The facts

- Version b11555 released on 2026-10-11
- Fix: AVX2 CPUs now use F16C when present

## Why it matters

Developers running Llama models on compatible CPUs will see faster inference without manual patches.

## Sources & references

1. [ggml-org/llama.cpp b11555](https://github.com/ggml-org/llama.cpp/releases/tag/b11555) – llama.cpp, 2026-10-11

Last updated: 2026-10-11