# llama.cpp release b11804 adds OpenCL argmax support

> The open-source LLM runtime updates with F32‑to‑I32 argmax for OpenCL and new binaries for macOS, Linux and iOS.

Oossa · 2026-10-22 · https://oossa.com/en/llama-cpp-release-b11804-adds-opencl-argmax-support

ggml‑org released version b11804 of llama.cpp on 2026‑10‑22. The update adds an OpenCL routine that computes argmax from 32‑bit floats to 32‑bit integers, improving GPU inference speed. It also includes fresh pre‑built binaries for Apple Silicon, Intel macOS, iOS, and several Ubuntu flavors (CPU, Vulkan, CUDA). The changes are authored by OpenCode and Li He of Qualcomm.

## The facts

- Release version b11804 published on 2026‑10‑22
- Adds OpenCL F32‑to‑I32 ARGMAX operation

## Why it matters

Developers can now run llama.cpp models faster on OpenCL‑compatible GPUs, expanding hardware options for hobbyist AI projects.

## Sources & references

1. [ggml-org/llama.cpp b11804](https://github.com/ggml-org/llama.cpp/releases/tag/b11804) – llama.cpp, 2026-10-22

Last updated: 2026-10-22