Draft page

This page is an outline. It describes what will be covered and is not yet complete technical documentation.

llm-inference is already installed on MareNostrum 5. You do not build or install anything — you load it as a module.

Requirements

  • A MareNostrum 5 account with access to the GPU partition (acc).
  • A valid Slurm billing account.

Load the module

Load llm-inference
module load EB/apps
module use /apps/ACC/LLM-INFERENCE/modulefiles
module load llm-inference/0.0.1-GCCcore-13.2.0

Verify

llm-inference --version
llm-inference --help

If llm-inference is not found, the module use line did not take effect — check the path and re-run the three commands in order.

Make it permanent

Avoid retyping this every session

Add the first two lines to your ~/.bashrc:

echo 'module load EB/apps' >> ~/.bashrc
echo 'module use /apps/ACC/LLM-INFERENCE/modulefiles' >> ~/.bashrc

The module load llm-inference/... line is deliberately left out, so you stay in control of which version you use.

Confirm your model is available

Before launching anything, check the allow list:

llm-inference model list

The table shows, per model: ID, family, data type, allowed GPU range, multi-node support, and whether the deployed vLLM can load it right now. The SUPPORTED column must read yes.

Next

Run your first job: Quickstart.