6688 Commits

Author SHA1 Message Date
Michael Mayer
52620fdb34
[R] Improve more docstrings (#9919) 2023-12-26 17:30:13 +08:00
Jiaming Yuan
6a5f6ba694
[CI] Add timeout for distributed GPU tests. (#9917) 2023-12-24 00:09:05 +08:00
Michael Mayer
b807f3e30c
[R] improve docstrings for "xgb.Booster.R" (#9906) 2023-12-21 10:01:30 +08:00
david-cortes
252e018275
correct name of function in header (#9905) 2023-12-20 10:52:00 +08:00
Jiaming Yuan
9d122293bc
[doc] Fix typo. [skip ci] (#9904) 2023-12-20 09:17:00 +08:00
david-cortes
ae32936ba2
[R] Catch C++ exceptions (#9903) 2023-12-19 10:45:03 +08:00
david-cortes
ff3d82c006
[R] Refactor field logic for dmatrix (#9901) 2023-12-18 20:31:01 +08:00
Jiaming Yuan
0edd600f3d
[doc] Brief introduction to base_score. (#9882) 2023-12-17 13:34:34 +08:00
david-cortes
db7f952ed6
update docs for parameters (#9900) 2023-12-16 12:19:22 +08:00
Dmitry Razdoburdin
2a6ab2547d
SYCL inference optimization (#9876)
---------

Co-authored-by: Dmitry Razdoburdin <>
2023-12-15 11:04:39 +08:00
Jiaming Yuan
1c6e031c75
[R] Fix clang warning. (#9874) 2023-12-15 01:30:43 +08:00
Jiaming Yuan
125bc812f8
[doc] Reference enable_categorical doc in sklearn. (#9884) 2023-12-14 23:29:19 +08:00
Jiaming Yuan
1aa8c8d9be
Support more scipy types. (#9881) 2023-12-14 18:28:37 +08:00
david-cortes
cd473c9da3
[R] enable multi-dimensional base_margin (#9885) 2023-12-14 09:16:53 +08:00
Philip Hyunsu Cho
936b22fdf3
[CI] Upload libxgboost4j.dylib (M1) to S3 bucket (#9886)
* [CI] Upload libxgboost4j.dylib (M1) to S3 bucket

* Fix typo
2023-12-13 15:25:51 -08:00
david-cortes
42173d7bc3
[doc] Clarify the effect of enable_categorical (#9877) 2023-12-13 08:39:41 +08:00
github-actions[bot]
d530d37707
[CI] Update RAPIDS to latest stable (#9857) 2023-12-12 22:58:03 +09:00
Dmitry Razdoburdin
43897b8296
Sycl implementation for objective functions (#9846)
---------

Co-authored-by: Dmitry Razdoburdin <>
2023-12-12 14:41:50 +08:00
david-cortes
ddab49a8be
[doc][R] Update arguments for ellipsis in predict (#9868) 2023-12-12 12:13:47 +08:00
Jiaming Yuan
faf0f2df10
Support dataframe data format in native XGBoost. (#9828)
- Implement a columnar adapter.
- Refactor Python pandas handling code to avoid converting into a single numpy array.
- Add support in R for transforming columns.
- Support R data.frame and factor type.
2023-12-12 09:56:31 +08:00
Jiaming Yuan
b3700bbb3f
Flexible find protobuf. (#9867) 2023-12-12 07:34:01 +08:00
david-cortes
562352101d
[R] Move all DMatrix fields to function arguments (#9862) 2023-12-10 02:45:28 +08:00
Jiaming Yuan
1094d6015d
[py] Use the first found native library. (#9860) 2023-12-08 17:23:16 +08:00
Jiaming Yuan
42de9206fc
Support multi-target, fit intercept for hinge. (#9850) 2023-12-08 05:50:41 +08:00
Jiaming Yuan
39c637ee19
Use array interface in Python prediction return. (#9855) 2023-12-08 03:42:14 +08:00
david-cortes
2c0fc97306
Remove note about multi-quantile being python-only (#9854) 2023-12-07 05:17:15 +08:00
david-cortes
9e9d41b95c
[R] Add note about serialization of DMatrix objects (#9853) 2023-12-07 03:11:15 +08:00
Jiaming Yuan
4bc1f3a388
[R] Bump requirement to 4.3.0. (#9847) 2023-12-07 00:12:45 +08:00
david-cortes
1de3f4135c
[R] Enable vector-valued parameters (#9849) 2023-12-06 20:32:20 +08:00
david-cortes
0716c64ef7
[R] Error out on multidimensional arrays (#9852) 2023-12-06 17:43:51 +08:00
david-cortes
62571b79eb
[R] Enable multi-output objectives (#9839) 2023-12-06 03:13:14 +08:00
david-cortes
9c56916fd7
[R] Very small performance tweaks (#9837) 2023-12-04 18:40:45 +08:00
Dmitry Razdoburdin
381f1d3dc9
Add support inference on SYCL devices (#9800)
---------

Co-authored-by: Dmitry Razdoburdin <>
Co-authored-by: Nikolay Petrov <nikolay.a.petrov@intel.com>
Co-authored-by: Alexandra <alexandra.epanchinzeva@intel.com>
2023-12-04 16:15:57 +08:00
david-cortes
7196c9d95e
[R] Fix memory safety issues (#9823) 2023-12-02 13:43:50 +08:00
Jiaming Yuan
e78b46046e
[CI] Update R version on Linux. (#9835) 2023-12-02 11:03:17 +08:00
Jiaming Yuan
2d8c67d6dc
[jvm-packages] Bump dependencies. (#9827)
- #9811
- #9814
- #9826
- #9830
- #9833
- #9832
- #9831
- #9834
2023-12-02 07:34:56 +08:00
david-cortes
95af5c074b
more usage of array interface, fix potential memory leaks of std::string (#9824) 2023-12-01 00:06:59 +08:00
david-cortes
37da66f865
[R] Use array interface for dense DMatrix creation (#9816)
---------

Co-authored-by: Jiaming Yuan <jm.yuan@outlook.com>
2023-11-30 04:35:05 +08:00
Yuan (Terry) Tang
da3d55db5b
Update affiliation (#9822) 2023-11-30 03:27:05 +08:00
Jiaming Yuan
e2e089ce12
[jvm-packages] Bump rapids version. (#9820) 2023-11-29 15:51:07 +08:00
david-cortes
c0ef2f8dce
[R] Fix potential memory leaks in case of R allocation failures (#9817) 2023-11-29 13:14:17 +08:00
Jiaming Yuan
59684b2db6
[doc] Draft for language binding consistency. [skip ci] (#9755) 2023-11-29 13:13:40 +08:00
david-cortes
bfa1252fca
[R][doc] Update docs about fitting from CSR (#9818) 2023-11-29 05:42:41 +08:00
Jiaming Yuan
34a2616696
[jvm-packages] Update dependencies. (#9809)
- scalatest: 3.2.17
- maven-checkstyle-plugin: 3.3.1
- maven-surefire-plugin: 3.2.2
- maven-project-info-reports-plugin: 3.5.0
- maven-javadoc-plugin: 3.6.2
2023-11-27 20:09:25 +08:00
Jiaming Yuan
e9f149481e
[sklearn] Fix loading model attributes. (#9808) 2023-11-27 17:19:01 +08:00
Jiaming Yuan
3f4e22015a
Mark NCCL python test optional. (#9804)
Skip the tests if XGBoost is not compiled with dlopen.
2023-11-25 11:25:47 +08:00
Jiaming Yuan
8fe1a2213c
Cleanup code for distributed training. (#9805)
* Cleanup code for distributed training.

- Merge `GetNcclResult` into nccl stub.
- Split up utilities from the main dask module.
- Let Channel return `Result` to accommodate nccl channel.
- Remove old `use_label_encoder` parameter.
2023-11-25 09:10:56 +08:00
Jiaming Yuan
e9260de3f3
[breaking] Remove dense libsvm parser plugin. (#9799) 2023-11-23 00:12:39 +08:00
Jiaming Yuan
1877cb8e83
Change default metric for gamma regression to deviance. (#9757)
* Change default metric for gamma regression to deviance.

- Cleanup the gamma implementation.
- Use deviance instead since the objective is derived from deviance.
2023-11-22 21:17:48 +08:00
Jiaming Yuan
0715ab3c10
Use dlopen to load NCCL. (#9796)
This PR adds optional support for loading nccl with `dlopen` as an alternative of compile time linking. This is to address the size bloat issue with the PyPI binary release.
- Add CMake option to load `nccl` at runtime.
- Add an NCCL stub.

After this, `nccl` will be fetched from PyPI when using pip to install XGBoost, either by a user or by `pyproject.toml`. Others who want to link the nccl at compile time can continue to do so without any change.

At the moment, this is Linux only since we only support MNMG on Linux.
2023-11-22 19:27:31 +08:00