====== Running Ollama on the HPC Cluster ======

===== Starting an interactive session for the ollama user service =====

  * Load slurm utils (sinteractive)

<code bash>
module load slurm/utils
</code>

  * Start an interactive session using sinteractive, see : https://hpc.wiki.utwente.nl/slurm:sinteractive

<code bash>
sinteractive --gres=gpu:1
</code>

wait until you got resources assigned !!

==== Starting the ollama server and interacting with it ====

  * Once you got an interactive session with gpu (a bit crowded right now), load the module ollama and start the user daemon

<code bash>
module load ollama/0.1.41
start-ollama
</code>

  * Now you can use the download, list, run commands of ollama (here for example : run llama3)

<code bash>
ollama run llama3
</code>

  * Once completed you can stop the user daemon and terminate the interactive session

<code bash>
stop-ollama
exit
</code>