# llama.cpp adds ARM NEON fp32‑to‑fp16 conversion in v b11761

> The Oct 21, 2026 release fixes a hidden bug in the ARM NEON path, enabling hardware fp32‑to‑fp16 conversion for faster inference on Apple Silicon and other ARM CPUs.

Oossa · 2026-10-20 · https://oossa.com/en/llama-cpp-adds-arm-neon-fp32-to-fp16-conversion-in-v-b11761

The open‑source llama.cpp library released version b11761 on Oct 21, 2026. It corrects the NEON branch so the fp32‑to‑fp16 conversion now uses the hardware instruction instead of a software fallback. The change also adds a compile‑time error to catch similar macro mismatches. The fix applies to macOS Apple Silicon, Linux ARM64, and Android ARM devices listed in the release notes.

## The facts

- Release date: 2026-10-21 ("Wed Oct 21 2026")
- Adds NEON fp32→fp16 hardware conversion for ARM CPUs

## Why it matters

ARM‑based users will see faster model inference because the library now uses the processor’s native half‑precision conversion.

## Sources & references

1. [ggml-org/llama.cpp b11761](https://github.com/ggml-org/llama.cpp/releases/tag/b11761) – llama.cpp, 2026-10-20

Last updated: 2026-10-20