Skip to content

[DMN][WIP] Experimental multi-GPU Polars testing#18335

Closed
rjzamora wants to merge 48 commits intorapidsai:branch-25.06from
rjzamora:cudf-polars-multi-combined
Closed

[DMN][WIP] Experimental multi-GPU Polars testing#18335
rjzamora wants to merge 48 commits intorapidsai:branch-25.06from
rjzamora:cudf-polars-multi-combined

Conversation

@rjzamora
Copy link
Member

@rjzamora rjzamora commented Mar 20, 2025

Description

This branch combines several in-flight PRs and includes a benchmarking script (for temporary convenience). This PR will never be merged, but will be kept open until it is roughly identical to branch-25.06 (aside from the benchmarking script).

Related PRs:

Checklist

  • I am familiar with the Contributing Guidelines.
  • New or existing tests cover these changes.
  • The documentation is up to date with these changes.

@rjzamora rjzamora added feature request New feature or request 2 - In Progress Currently a work in progress non-breaking Non-breaking change cudf-polars Issues specific to cudf-polars labels Mar 20, 2025
@rjzamora rjzamora self-assigned this Mar 20, 2025
@copy-pr-bot
Copy link

copy-pr-bot bot commented Mar 20, 2025

Auto-sync is disabled for draft pull requests in this repository. Workflows must be run manually.

Contributors can view more details about this message here.

@github-actions github-actions bot added the Python Affects Python cuDF API. label Mar 20, 2025
@rjzamora
Copy link
Member Author

cc @pentschev @quasiben - I decided to open a PR for cudf-polars-multi-combined to make it easier for us to discuss (and for others to push to my branch).

rapids-bot bot pushed a commit to rapidsai/rapidsmpf that referenced this pull request Mar 26, 2025
This is a follow-up to #150

Closes #157

The goal of this PR is to simplify memory-resource creation by avoiding it in `rapidsmp` altogether. Since the user can just use `LocalCUDACluster` to deploy a Dask cluster, they can also use existing options/utilities to create a memory pool on each worker. When `rapidsmp.integrations.dask.bootstrap_dask_cluster` is called, each worker only needs to wrap the current memory resource in a `StatisticsResourceAdaptor`.

This is technically "breaking", because it removes the `pool_size` argument from `bootstrap_dask_cluster`. However, we are only using that option in rapidsai/cudf#18335 (which is still experimental - and can be easily changed).

Authors:
  - Richard (Rick) Zamora (https://github.com/rjzamora)

Approvers:
  - Tom Augspurger (https://github.com/TomAugspurger)
  - Peter Andreas Entschev (https://github.com/pentschev)

URL: #172
@copy-pr-bot
Copy link

copy-pr-bot bot commented Apr 10, 2025

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@rjzamora rjzamora force-pushed the cudf-polars-multi-combined branch from d3f05bb to 3185f7d Compare April 25, 2025 17:58
@rjzamora
Copy link
Member Author

rjzamora commented May 2, 2025

Closing as this functionality is now in branch-25.06 and #18461

@rjzamora rjzamora closed this May 2, 2025
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

2 - In Progress Currently a work in progress cudf-polars Issues specific to cudf-polars feature request New feature or request non-breaking Non-breaking change Python Affects Python cuDF API.

Projects

Archived in project

Development

Successfully merging this pull request may close these issues.

1 participant