# llama.cpp adds Hexagon‑accelerated softplus operation

> The open‑source llama.cpp library now runs the softplus activation on Qualcomm Hexagon NPU, improving performance on supported Android devices.

Oossa · 2026-10-17 · https://oossa.com/en/llama-cpp-adds-hexagon-accelerated-softplus-operation

The llama.cpp project released version b11703 on Oct 17, 2026. It adds a vectorised softplus function that runs on Qualcomm’s Hexagon NPU (HVX). The new helper uses existing Hexagon primitives for exp and log, so the math stays the same as the CPU version. The change is listed under the Android arm64 build that supports Snapdragon CPUs, Adreno GPUs and Hexagon NPUs.

## The facts

- Release date: Oct 17, 2026
- Adds HVX‑accelerated softplus for Android Snapdragon devices

## Why it matters

Developers can now run LLM inference faster on phones with Hexagon NPUs, extending llama.cpp’s low‑power use cases.

## Sources & references

1. [ggml-org/llama.cpp b11703](https://github.com/ggml-org/llama.cpp/releases/tag/b11703) – llama.cpp, 2026-10-17

Last updated: 2026-10-17