Skip to content

Ensure alignment can be passed to MemoryResource.allocate() #634

Open

Description

@leofang

Unlike in C++ I think it'd have to be an optional keyword argument, for a few reasons

  • To preserve backward compatibility (of both cuda.core and RMM Python)
  • To improve UX (passing an explicit alignment is less common use case, especially if the underlying MR does not support any custom alignment)

Activity

  1. added
    enhancementAny code-related improvements
    triageNeeds the team's attention
    cuda.coreEverything related to the cuda.core module
    on May 13, 2025
  2. added
    P2Low priority - Nice to have
    and removed
    triageNeeds the team's attention
    on Oct 15, 2025
  3. removed this from the cuda.core backlog milestone on Apr 2, 2026
  4. removed their assignment
    on Nov 4, 2026
  5. removed theissue type on Nov 4, 2026
  6. FayezBast commented on Nov 5, 2026

    @FayezBast

    hi @leofang interested in doing this , if u dont have a problem

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Metadata

Metadata

Assignees

No one assigned

    Labels

    P2Low priority - Nice to havecuda.coreEverything related to the cuda.core moduleenhancementAny code-related improvements

    Type

    No type

    Projects

    • Status
      Todo

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions