rapidsai / rapidsai/deployment

Broken AzureML startup script

Open
#711 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Jupyter Notebook
Stars
15
Forks
41
Avg merge
1d 8h
Merged PRs (30d)
6

Description

The script in https://docs.rapids.ai/deployment/nightly/cloud/azure/azureml/#provision-rapids-setup-script creates a situation in azure ML where we end up with the wrong python path. In the notebook:

!conda info
   active environment : rapids
    active env location : /anaconda/envs/rapids
       user config file : /home/azureuser/.condarc
 populated config files : /anaconda/.condarc
                          /anaconda/condarc.d/anaconda-auth.yml
          conda version : 25.11.1
    conda-build version : not installed
         python version : 3.13.11.final.0
! which python
/anaconda/envs/azureml_py38/bin//python 
import cudf
cudf.__file__
'/anaconda/envs/rapids/lib/python3.13/site-packages/cudf/__init__.py'

We think the issue might be that the PATH variable has the /anaconda/envs/azureml_py38/bin//python set first, and then the CONDA_PREFIX later.

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 with the Provision RAPIDS setup script linked in the AzureML deployment documentation, then reproduce the notebook checks for conda info, which python, and cudf.file. Trace how PATH and CONDA_PREFIX are configured. Done means AzureML resolves Python from the intended rapids environment and the imported cudf path matches that environment.

Written by the indexing model from the issue text.

Assessment

Tech stack
azure, jupyter-notebook, python
Domain
cloud, devops
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Quiet
Clarity
Mostly clear
Newbie friendliness
58/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.