-
Notifications
You must be signed in to change notification settings - Fork 197
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Use rmm allocator in CAGRA prune #1503
Conversation
@tfeher Can you review the code and let me know if there are any problems? |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks @enp1s0 for the PR! It looks good overall, I have just a few smaller comments.
Thanks @tfeher for your review! I have modified the issues you have pointed out. |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Thanks @enp1s0 for addressing the issues! The PR looks good to me.
/merge |
This PR changes CAGRA `knn_graph_sort` function to use `raft::util::bitnic_sort` instead of a custom sorting function. Rel: #1503 (comment) Authors: - tsuki (https://github.com/enp1s0) - Corey J. Nolet (https://github.com/cjnolet) Approvers: - Tamas Bela Feher (https://github.com/tfeher) URL: #1550
This PR modifies the CAGRA prune function to use rmm allocator instead of a custom memory allocator. And also removes the multi-GPU functionality that is not suitable for the RAFT policy.
rel: #1461