# llama.cpp release adds OpenCL fixes for Adreno 623 GPUs

> The Oct 9 2026 update prevents shader crashes on A6x devices and adds the Adreno 623 to GPU detection.

Oossa · 2026-10-09 · https://oossa.com/en/llama-cpp-release-adds-opencl-fixes-for-adreno-623-gpus

The open‑source llama.cpp library released version b11533 on 2026‑10‑09. It fixes OpenCL kernel compilation on A6x GPUs, which were crashing on devices with an Adreno 623 chip. The patch skips a problematic kernel and adds a constant‑fold workaround for GEMV kernels. It also updates the GPU detection list to recognise the Adreno 623. Users of Linux, macOS or iOS can download pre‑built binaries from the release page.

## The facts

- Release version b11533 published on Fri Oct 09 2026
- Adds OpenCL fix for A6x GPUs with Adreno 623

## Why it matters

Developers can now run llama.cpp on Android devices with Adreno 623 GPUs without compiler crashes.

## Sources & references

1. [ggml-org/llama.cpp b11533](https://github.com/ggml-org/llama.cpp/releases/tag/b11533) – llama.cpp, 2026-10-09

Last updated: 2026-10-09