# llama.cpp adds OpenCL kernel for Qualcomm Adreno X1 GPUs

> Version b11702, released Oct 17 2026, includes a new MxFP4 MoE bin kernel that speeds up LLM inference on Adreno X1 devices.

Oossa · 2026-10-17 · https://oossa.com/en/llama-cpp-adds-opencl-kernel-for-qualcomm-adreno-x1-gpus

The ggml‑org/llama.cpp project released version b11702 on Oct 17 2026. The update adds an OpenCL kernel called `gemm_moe_mxfp4_q8_1_dp4a_ila_ldck` for Qualcomm Adreno X1 GPUs. The change is part of a set of OpenCL tweaks, including whitespace fixes and DP4A support for X1E. Binary builds for macOS, iOS, and several Ubuntu flavors are also provided.

## The facts

- Release tag b11702 published on 2026-10-17 ("Sat Oct 17 2026 02:21:45 GMT+0200").
- New kernel name: gemm_moe_mxfp4_q8_1_dp4a_ila_ldck for Adreno X1 devices.

## Why it matters

The kernel lets developers run LLMs faster on Android phones that use Adreno X1 GPUs.

## Sources & references

1. [ggml-org/llama.cpp b11702](https://github.com/ggml-org/llama.cpp/releases/tag/b11702) – llama.cpp, 2026-10-17

Last updated: 2026-10-17