FICHA · AUR

llama.cpp-sycl

llama.cpp with Intel Arc GPU acceleration via SYCL/oneAPI. Please read the README on GitHub before use.

  • llm-inference-tool
  • CLI
  • Dev
  • Launchable
  • Runs in terminal
official+codex · reviewed · Jun 2, 2026 description in en

Description

Intel Arc GPUs can accelerate llama.cpp through a SYCL and oneAPI build.

This package is useful for users with compatible Intel GPU hardware who accept the setup requirements documented upstream. It is an optimized inference variant, not a beginner one-click AI app.

SYCL and oneAPI setups can be driver-sensitive. Read the upstream README and test before production use.

How to run

llama-cli

Commands: llama-cli

Permissions

Permissions not analysed for this source yet.