ollama / ollama/ollama-python

GPU Selection & Device Specification

Open
#161 2 comments 8 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
10.5k
Forks
1.2k
Avg merge
4m
Merged PRs (30d)
1

Description

I would like to suggest a feature that would allow specifing which GPU or GPUs to run on directly within the Ollama Python library.

This feature is crucial in shared server environments across multiple GPUs and multiple users, as it allows each Jupyter notebook to run on the corresponding GPU without conflicts. Currently, specifying GPU usage in Ollama is somewhat complex. A streamlined method to assign tasks to specific GPUs directly inside the Python program would prevent conflicts and optimize workflow. Implementing this feature would significantly improve usability and align Ollama with other machine-learning frameworks.

Thank you for considering this suggestion. I would be happy to discuss further details if needed.

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start by reviewing the Ollama Python library API and how GPU usage is currently specified in Ollama. Define the Python-facing behavior needed to select one or more GPUs from a Jupyter notebook, with completion demonstrated by independent notebook tasks using their assigned GPUs without conflicts.

Written by the indexing model from the issue text.

Assessment

Tech stack
ollama, python
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Quiet
Clarity
Needs clarification
Newbie friendliness
38/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.