FICHA · AUR

llama.cpp-sycl-f32

Port of Facebook's LLaMA model in C/C++ (with Intel SYCL GPU optimizations and F32)

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

Description

Intel SYCL GPU acceleration with F32 math can favor compatibility or precision for local LLM inference.

This package is useful for users who want the single-precision SYCL variant of llama.cpp. It is a backend-specific inference build, not a model source.

F32 execution can use more memory than F16. Check GPU capacity before loading large models.

How to run

llama-cli

Commands: llama-cli

Permissions

Permissions not analysed for this source yet.