roboflow / roboflow/inference

Importing get_model is super slow

Open
#1,840 1 comment 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

bug
Dominant language
Python
Stars
2.5k
Forks
319
Avg merge
1d 14h
Merged PRs (30d)
133

Description

Search before asking
  • I have searched the Inference issues and found no similar bug report.
Bug

Running uv run python -c "import time; start = time.time(); from inference import get_model; print(f'Import took: {time.time() - start:.2f}s')" takes 120-150seconds on my machine. I presume this is because of some heavy work being done at import time. Is it possible to disable this?

Environment

Python 3.11 and inference 0.63.1. Happens for me on both MacOS and Linux

Minimal Reproducible Example
uv run python -c "import time; start = time.time(); from inference import get_model; print(f'Import took: {time.time() - start:.2f}s')"
Additional

No response

Are you willing to submit a PR?
  • Yes I'd like to help by submitting a PR!

Contributor guide

Open the contributing guide

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 running the reported Python 3.11 reproduction command on macOS or Linux and trace the import path for inference.get_model. Identify the work responsible for the 120–150 second import, then verify that importing get_model completes substantially faster while remaining usable.

Written by the indexing model from the issue text.

Assessment

Tech stack
python
Domain
performance
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
48/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.