Skip to content

[wip][mt] Unify the histogram kernels. #11901

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.

Sign up for GitHub

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

Jump to bottom
Closed
trivialfis wants to merge 5 commits into from
Closed

[wip][mt] Unify the histogram kernels. #11901

trivialfis wants to merge 5 commits into from

Conversation

@trivialfis
Copy link
Member

@trivialfis trivialfis commented Jan 2, 2026 •
edited
Loading

stacked on #11895 .

  • Merge the kernels of single-target and vector-leaf.
  • Make on-the-fly fixed point conversion optional.

ref #9043

  • Avoid duplicated gradient by moving f32 gradient into the hist builder.
  • Merge tests.
  • Avoid cache in the sampler.

@trivialfis
Implement vector load for the GPU compressed iterator.
042d148 
- Extract the byte swap implementation.
- Use vector load for the GPU histogram kernel.
@trivialfis
copilot.
418435a
@trivialfis
Fix test.
370ceb6
@trivialfis
Use intrinsic instead.
8a023c4
@trivialfis
[mt] Unify the histogram kernels.
1c3a521 
- Merge the kernels of single-target and vector-leaf.
- Make on-the-fly fixed point conversion optional.
@trivialfis trivialfis marked this pull request as draft January 2, 2026 00:17
@trivialfis trivialfis closed this Jan 5, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

No reviews

Assignees

No one assigned

Labels

None yet

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

1 participant

@trivialfis