Scalable, Portable and Distributed Gradient Boosting (GBDT, GBRT or GBM) Library, for Python, R, Java, Scala, C++ and more. Runs on single machine, Hadoop, Spark, Dask, Flink and DataFlow


eXtreme Gradient Boosting

Build Status Build Status Build Status XGBoost-CI Documentation Status GitHub license CRAN Status Badge PyPI version Conda version Optuna Twitter

Community | Documentation | Resources | Contributors | Release Notes

XGBoost is an optimized distributed gradient boosting library designed to be highly efficient, flexible and portable. It implements machine learning algorithms under the Gradient Boosting framework. XGBoost provides a parallel tree boosting (also known as GBDT, GBM) that solve many data science problems in a fast and accurate way. The same code runs on major distributed environment (Kubernetes, Hadoop, SGE, MPI, Dask) and can solve problems beyond billions of examples.


© Contributors, 2019. Licensed under an Apache-2 license.

Contribute to XGBoost

XGBoost has been developed and used by a group of active community members. Your help is very valuable to make the package better for everyone. Checkout the Community Page.


  • Tianqi Chen and Carlos Guestrin. XGBoost: A Scalable Tree Boosting System. In 22nd SIGKDD Conference on Knowledge Discovery and Data Mining, 2016
  • XGBoost originates from research project at University of Washington.


Become a sponsor and get a logo here. See details at Sponsoring the XGBoost Project. The funds are used to defray the cost of continuous integration and testing infrastructure (

Open Source Collective sponsors

Backers on Open Collective Sponsors on Open Collective


[Become a sponsor]



[Become a backer]

Other sponsors

The sponsors in this list are donating cloud hours in lieu of cash donation.

Amazon Web Services

  • Predict error in R as of 1.1.1

    Predict error in R as of 1.1.1

    R version: 3.6.1 (Action of the Toes) xgboost version:

    This error can be produced when attempting to call predict on an xgboost model developed pre-1.0

    Error: Error in predict.xgb.Booster(model, data) : [11:24:23] amalgamation/../src/ Check failed: mparam_.num_feature != 0 (0 vs. 0) : 0 feature is supplied. Are you using raw Booster interface?

    opened by jrausch12 103
  • [jvm-packages] Scala implementation of the Rabit tracker.

    [jvm-packages] Scala implementation of the Rabit tracker.


    The Java implementation of RabitTracker in xgboost4j depends on the Python script in dmlc-core to handle all socket connections / loggings.

    The reliance on Python code has a few weaknesses:

    • It makes xgboost4j-spark and xgboost4j-flink, which use RabitTracker, more susceptible to random failures on worker nodes due to Python versions.
    • It increases difficulty for debugging tracker-related issues.
    • Since the Python code handles all socket connection logic, it is difficult to handle timeout due to connection issues, and thus the tracker may hang indefinitely if the workers fail to connect due to networking issues.

    To address the above issues, this PR was created to introduce a pure Scala implementation of the RabitTracker, that is interchangeable with the Java implementation at interface level, but with the Python dependency completely removed.

    The implementation was tested in a Spark cluster running on YARN with up to 16 distributed workers. More thorough tests (local mode, more nodes etc.) of this PR is still WIP.

    Implementation details

    The Scala version of RabitTracker replicates the functionality of the RabitTracker class in, that is, to handle incoming connections from Rabit clients of the worker nodes, compute the link map and rank for each given worker, and print tracker logging information.

    The tracker handles connections in asynchronous and non-blocking fashion using Akka, and resolves the inter-dependency between worker connections properly.


    The Scala RabitTracker implements timeout logic at multiple entry points.

    • RabitTracker.start()may time out if the tracker fails to bind to a socket address within certain time limit.
    • RabitTracker.waitFor() may time out if at least one worker fails to connect to the tracker within certain time limit. This prevents the tracker from hanging forever.
    • RabitTracker.waitFor() may time out after a given maximum execution time limit.


    The following tasks are to be completed:

    • [x] Add options to switch between Python-based tracker and Scala-based tracker in xgboost4j-spark and xgboost4j-flink.
    • [x] Refactoring of RabitTracker.scala to separate the components into different files.
    • [x] Unit tests for individual actors (using akka-testkit).
    • [x] Test with rabit clients (Allreduce, checkpoint, simulated connection issus.)
    • [x] Test in production.
    opened by xydrolase 83
  • Model produced in 1.0.0 cannot be loaded into 0.90

    Model produced in 1.0.0 cannot be loaded into 0.90

    Following the instructions here:

    > install.packages("drat", repos="")
    trying URL ''
    Content type 'application/zip' length 87572 bytes (85 KB)
    downloaded 85 KB
    package ‘drat’ successfully unpacked and MD5 sums checked
    The downloaded binary packages are in
    > drat:::addRepo("dmlc")
    > install.packages("xgboost", repos="", type = "source")
    Warning: unable to access index for repository
      Line starting '<!DOCTYPE html> ...' is malformed!
    Warning message:
    package ‘xgboost’ is not available (for R version 3.6.0) 

    It also fails on R 3.6.2 with the same error.

    Note: I would much prefer to use the CRAN version. But models I train on linux and Mac and save using the saveRDS function don't predict on another system (windows), they just produce numeric(0). If anyone has any guidelines on how to save an XGBoost model for use on other computers, please let me know. I've tried and xgb.load - both produce numeric(0) as well. But on the computer I trained the model on (a month ago), readRDS in R works just fine. Absolutely baffling to me.

    opened by leedrake5 74
  • pip install failure

    pip install failure

    [email protected]:/# pip install xgboost Downloading/unpacking xgboost Could not find a version that satisfies the requirement xgboost (from versions: 0.4a12, 0.4a13) Cleaning up... No distributions matching the version for xgboost Storing debug log for failure in /root/.pip/pip.log

    You can repeat in docker with: docker run -it --rm ubuntu:trusty

    apt-get update
    apt-get install python-pip
    pip install xgboost

    see this also:

    opened by cliveseldon 72
  • OMP: Error #15: Initializing libiomp5.dylib, but found libiomp5.dylib already initialized.

    OMP: Error #15: Initializing libiomp5.dylib, but found libiomp5.dylib already initialized.

    For bugs or installation issues, please provide the following information. The more information you provide, the more easily we will be able to offer help and advice.

    Environment info

    Operating System: Mac OSX Sierra 10.12.1


    Package used (python):

    xgboost version used: xgboost 0.6a2

    If you are using python package, please provide

    1. The python version and distribution: Pythong 2.7.12
    2. The command to install xgboost if you are not installing from source pip install xgboost

    Steps to reproduce

    1. from xgboost import XGBClassifier import numpy as np import matplotlib.pyplot as plt x = np.array([[1,2],[3,4]]) y = np.array([0,1]) clf = XGBClassifier(base_score = 0.005),y) plt.hist(clf.feature_importances_)

    What have you tried?

    See the error message: "OMP: Error #15: Initializing libiomp5.dylib, but found libiomp5.dylib already initialized. OMP: Hint: This means that multiple copies of the OpenMP runtime have been linked into the program. That is dangerous, since it can degrade performance or cause incorrect results. The best thing to do is to ensure that only a single OpenMP runtime is linked into the process, e.g. by avoiding static linking of the OpenMP runtime in any library. As an unsafe, unsupported, undocumented workaround you can set the environment variable KMP_DUPLICATE_LIB_OK=TRUE to allow the program to continue to execute, but that may cause crashes or silently produce incorrect results. For more information, please see"

    I tried: import os os.environ['KMP_DUPLICATE_LIB_OK']='True'

    It can do the job for me. But it is kind of ugly.

    I know it might be not the problem of xgboost, but I'm pretty sure this problem happened after I upgrade xgboost using 'pip install xgboost'. I post the issue here to see if someone had the same problem as me. I have very little knowledge about OpenMP. Please help!
    Thanks in advance!

    opened by symPhysics 71
  • RMM integration plugin

    RMM integration plugin

    Fixes #5861.

    Depends on #5871. Will rebase after #5871 is merged.

    Depends on #5966. Will rebase after #5966 is merged.

    ~Currently, the C++ tests are crashing with an out-of-memory error.~ The OOM has been fixed.

    status: need review 
    opened by hcho3 66
  • [DISCUSSION] Adopting JSON-like format as next-generation model format

    [DISCUSSION] Adopting JSON-like format as next-generation model format

    As discussed in #3878 and #3886 , we might want a more extendable format for saving XGBoost model.

    For now my plan is utilizing the JSONReader and JSONWriter implemented in dmlc-core to add experimental support for saving/loading model into Json file. Due to the fact that related area of code is quite messy and is dangerous to change, I want to share my plan and possibly an early PR as soon as possible so that someone could point out my mistakes earlier(there will be mistakes), and we don't make duplicated work. :)


    type: roadmap 
    opened by trivialfis 57
  • XGBoost 0.90 Roadmap

    XGBoost 0.90 Roadmap

    This thread is to keep track of all the good things that will be included in 0.90 release. It will be updated as the planned release date (~May 1, 2019~ as soon as Spark 2.4.3 is out) approaches.

    • [x] XGBoost will no longer support Python 2.7, since it is reaching its end-of-life soon. This decision was reached in #4379.
    • [x] XGBoost4J-Spark will now require Spark 2.4+, as Spark 2.3 is reaching its end-of-life in a few months (#4377) (
    • [x] XGBoost4J now supports up to JDK 12 (#4351)
    • [x] Additional optimizations for gpu_hist (#4248, #4283)
    • [x] XGBoost as CMake target; C API example (#4323, #4333)
    • [x] GPU multi-class metrics (#4368)
    • [x] Scikit-learn-like random forest API (#4148)
    • [x] Bugfix: Fix GPU histogram allocation (#4347)
    • [x] [BLOCKING][jvm-packages] fix non-deterministic order within a partition (in the case of an upstream shuffle) on prediction
    • [x] Roadmap: additional optimizations for hist on multi-core Intel CPUs (#4310)
    • [x] Roadmap: hardened Rabit; see RFC #4250
    • [x] Robust handling of missing values in XGBoost4J-Spark
    • [x] External memory with GPU predictor (#4284, #4438)
    • [x] Use feature interaction constraints to narrow split search space (#4341)
    • [x] Re-vamp Continuous Integration pipeline; see RFC #4234
    • [x] Bugfix: AUC, AUCPR metrics should handle weights correctly for learning-to-rank task (#4216)
    • [x] Ignore comments in LIBSVM files (#4430)
    • [x] Bugfix: Fix AUCPR metric for ranking (#4436)
    type: roadmap 
    opened by hcho3 56
  • 1.5.0 Release Candidate

    1.5.0 Release Candidate

    Roadmap . Draft of release note: .

    We are about to release version 1.5.0 of XGBoost. In the next two weeks, we invite everyone to try out the release candidate (RC).

    Feedback period: until the end of October 13, 2021. No new feature will be added to the release; only critical bug fixes will be added.


    Available packages:

    • Python packages:
    pip install xgboost==1.5.0rc1
    • R packages: Linux x86_64: Windows x86_64:
    R CMD INSTALL ./xgboost_r_gpu_linux.tar.gz
    • JVM packages
    Show instructions (Maven/SBT)


        <id>XGBoost4J Release Repo</id>
        <name>XGBoost4J Release Repo</name>


    libraryDependencies ++= Seq(
      "ml.dmlc" %% "xgboost4j" % "1.5.0-RC1",
      "ml.dmlc" %% "xgboost4j-spark" % "1.5.0-RC1"
    resolvers += ("XGBoost4J Release Repo"
                  at "")

    Starting from 1.2.0, XGBoost4J-Spark supports training with NVIDIA GPUs. To enable this capability, download artifacts suffixed with -gpu, as follows:

    Show instructions (Maven/SBT)


        <id>XGBoost4J Release Repo</id>
        <name>XGBoost4J Release Repo</name>


    libraryDependencies ++= Seq(
      "ml.dmlc" %% "xgboost4j-gpu" % "1.5.0-RC1",
      "ml.dmlc" %% "xgboost4j-spark-gpu" % "1.5.0-RC1"
    resolvers += ("XGBoost4J Release Repo"
                  at "")


    • [x] Release pip rc package.
    • [x] Test on R-hub.
    • [x] Release R rc package.
    • [x] Release jvm rc packages.

    PRs to be backported

    • [x] Fix gamma negative log likelihood (
    • [x] Fix verbose_eval in Python cv function. (
    • [x] Fix weighted samples in multi-class AUC (
    • [x] Fix prediction with categorical dataframe using sklearn interface. (
    type: roadmap 
    opened by trivialfis 54
  • [DISCUSSION] Integration with PySpark

    [DISCUSSION] Integration with PySpark

    I just noticed that there are some requests for integration with PySpark

    I also received some emails from the users discussing the same topic

    I would like to initialize a discussion here on whether/when we shall start this work

    @tqchen @terrytangyuan

    type: python 
    opened by CodingCat 53
  • [Roadmap] XGBoost 1.0.0 Roadmap

    [Roadmap] XGBoost 1.0.0 Roadmap

    @dmlc/xgboost-committer please add your items here by editing this post. Let's ensure that

    • each item has to be associated with a ticket

    • major design/refactoring are associated with a RFC before committing the code

    • blocking issue must be marked as blocking

    • breaking change must be marked as breaking

    for other contributors who have no permission to edit the post, please comment here about what you think should be in 1.0.0

    I have created three new types labels, 1.0.0, Blocking, Breaking

    • [x] Improve installation experience on Mac OSX (#4477)
    • [x] Remove old GPU objectives.
    • [x] Remove gpu_exact updater (deprecated) #4527
    • [x] Remove multi threaded multi gpu support (deprecated) #4531
    • [x] External memory for gpu and associated dmatrix refactoring #4357 #4354
    • [ ] Spark Checkpoint Performance Improvement (
    • [x] [BLOCKING] the sync mechanism in hist method in master branch is broken due to the inconsistent shape of tree in different workers (,
    • [x] Per-node sync slows down distributed training with 'hist' (#4679)
    • [x] Regression tests including binary IO compatibility, output stability, performance regressions.
    type: roadmap 
    opened by CodingCat 52
  • [CI] Document the use of Docker wrapper script

    [CI] Document the use of Docker wrapper script

    It is useful to test Docker containers locally before making changes on the CI side.

    Rendered doc:

    @rongou @trivialfis Can one of you review?

    opened by hcho3 0
  • Cannot convert value of type NotImplementedType to cudf scalar

    Cannot convert value of type NotImplementedType to cudf scalar

    E           ValueError: Cannot convert value of type NotImplementedType to cudf scalar

    E   ValueError: Cannot convert value of type NotImplementedType to cudf scalar

    opened by hcho3 0
  • give rabit tracker a port number

    give rabit tracker a port number

    HI, All : when I use xgboost4j-spark on k8s and istio ,the training will hang for tracker waiting for worker .

    I found the reason. xgboost use AKKA as protocol between tracker and worker. but if I run Tracker in pod with Istio proxy. it will reject inbound communication from worker. so tracker will wait until time_out.

    I found solution for AKKA with Istio below:

    but it's require Tracker port is a fixed port , but xgboost given a random port for Now.

    I read the source code in code of RabitTracker.scala I found code below:

    private[scala] class RabitTracker(numWorkers: Int, port: Option[Int] = None,
                                      maxPortTrials: Int = 1000)

    and tracker start with code

    private def start(timeout: Duration): Boolean = {
        val hostAddress = Option(TrackerProperties.getInstance().getHostIp)
        handler ? RabitTrackerHandler.StartTracker(
          new InetSocketAddress(hostAddress, port.getOrElse(0)), maxPortTrials, timeout)
        // block by waiting for the actor to bind to a port
        Try(Await.result(handler ? RabitTrackerHandler.RequestBoundFuture, askTimeout.duration)
          .asInstanceOf[Future[Map[String, String]]]) match {
          case Success(futurePortBound) =>
            // The success of the Future is contingent on binding to an InetSocketAddress.
            val isBound = Try(Await.ready(futurePortBound, tcpBindingTimeout)).isSuccess
            if (isBound) {
              workerEnvs = Await.result(futurePortBound, 0 nano)
          case Failure(ex: Throwable) =>

    RabitTrackerHandler found a random port for tracker if port is None

    case msg: StartTracker =>
          maxPortTrials = msg.maxPortTrials
          workerConnectionTimeout = msg.connectionTimeout
          // if the port number is missing, try binding to a random ephemeral port.
          if (msg.addr.getPort == 0) {
            tcpManager ! Tcp.Bind(self,
              new InetSocketAddress(msg.addr.getAddress, new Random().nextInt(61000 - 32768) + 32768),
              backlog = 256)
          } else {
            tcpManager ! Tcp.Bind(self, msg.addr, backlog = 256)
          sender() ! true

    but in code of xgboost.scala I we didn't set port when create Tracker instance code as below:

    /** visiable for testing */
      private[scala] def getTracker(nWorkers: Int, trackerConf: TrackerConf): IRabitTracker = {
        val tracker: IRabitTracker = trackerConf.trackerImpl match {
          case "scala" => new RabitTracker(nWorkers)
          case "python" => new PyRabitTracker(nWorkers, trackerConf.hostIp, trackerConf.pythonExec)
          case _ => new PyRabitTracker(nWorkers)

    so if add an new option in TrackerConf

    case class TrackerConf(workerConnectionTimeout: Long, trackerImpl: String,
      hostIp: String = "", pythonExec: String = "" ,port:Option[Int]=None)

    and given a port if any settings not None

    /** visiable for testing */
     private[scala] def getTracker(nWorkers: Int, trackerConf: TrackerConf): IRabitTracker = {
       val tracker: IRabitTracker = trackerConf.trackerImpl match {
         case "scala" => new RabitTracker(nWorkers, trackerConf.port)
         case "python" => new PyRabitTracker(nWorkers, trackerConf.hostIp, trackerConf.pythonExec)
         case _ => new PyRabitTracker(nWorkers)

    we can support istio excludeInboundPort.

    opened by Francis-W 1
  • trainning failed with OOM error

    trainning failed with OOM error

    The training job failed with an OOM error while training with 8 years (2000-2008) input dataset from Fannie Mae website. Code: spark-rapids-example mortgage demo Env: 4 V100 GPUs with 32 GB of memory each spark3.2.*

    The rough estimate training dataset size is 1,098,139,175 rows * 28 columns * 4 byte floats = 114Gb, the total GPU memory in cluster is 4 V100 * 32 GB = 128GB, so it should not hit not OOM issue.

    log info:

    2022-09-29 22:22:41,591 ERROR [Executor task launch worker for task 1.0 in stage 6.0 (TID 204)] XGBoostSpark (XGBoost.scala:buildDistributedBooster(358)) - XGBooster worker 1 has failed 0 times due to [22:22:41] /workspace/src/tree/ Exception in gpu_hist: [22:22:41] /workspace/jvm-packages/xgboost4j-gpu/src/native/../../../../src/common/device_helpers.cuh:428: Memory allocation error on worker 3: Caching allocator
    - Free memory: 224067584
    - Requested memory: 878511352
    The output from the other four executors look like this:
    2022-09-29 22:22:41,595 ERROR [Executor task launch worker for task 3.0 in stage 6.0 (TID 205)] XGBoostSpark (XGBoost.scala:buildDistributedBooster(358)) - XGBooster worker 3 has failed 0 times due to [22:22:41] /workspace/src/tree/ Exception in gpu_hist: [22:22:41] /workspace/rabit/include/rabit/internal/utils.h:84: Allreduce failed
    Stack trace:
      [bt] (0) /tmp/ [0x7f2848c75f39]
      [bt] (1) /tmp/<xgboost::detail::GradientPairInternal<float> >*, xgboost::DMatrix*, std::vector<xgboost::RegTree*, std::allocator<xgboost::RegTree*> > const&)+0x695) [0x7f2848c971c5]
      [bt] (2) /tmp/<xgboost::detail::GradientPairInternal<float> >*, xgboost::DMatrix*, int, std::vector<std::unique_ptr<xgboost::RegTree, std::default_delete<xgboost::RegTree> >, std::allocator<std::unique_ptr<xgboost::RegTree, std::default_delete<xgboost::RegTree> > > >*)+0x7e3) [0x7f28488167c3]
      [bt] (3) /tmp/*, xgboost::HostDeviceVector<xgboost::detail::GradientPairInternal<float> >*, xgboost::PredictionCacheEntry*)+0x317) [0x7f2848817367]
      [bt] (4) /tmp/, std::shared_ptr<xgboost::DMatrix>)+0x312) [0x7f2848853212]
      [bt] (5) /tmp/ [0x7f28486f6118]
      [bt] (6) [0x7f7b2c8308f0]
    opened by nvliyuan 3
  • XGBoost corrupted the jvm memroy

    XGBoost corrupted the jvm memroy

    We run 14 xgboost in spark in parallel, but it throw out below error. it looks like the heap memory is coruppted. Do you know what's the issue? when we run single training model, there's no such error.

    A fatal error has been detected by the Java Runtime Environment:

    SIGSEGV (0xb) at pc=0x00007f1b028dab21, pid=23988, tid=0x00007f1acf826700

    JRE version: OpenJDK Runtime Environment (Zulu (8.0_202-b04) (build 1.8.0_202-b04)

    Java VM: OpenJDK 64-Bit Server VM (25.202-b04 mixed mode linux-amd64 compressed oops)

    Problematic frame:

    J 8901 C2 java.util.WeakHashMap.get(Ljava/lang/Object;)Ljava/lang/Object; (77 bytes) @ 0x00007f1b028dab21 [0x00007f1b028daa40+0xe1]

    Core dump written. Default location: /hadoop/1/yarn/local/usercache/jinmfeng/appcache/application_1663728370843_647527/container_e3798_1663728370843_647527_01_000053/core or core.23988

    An error report file with more information is saved as:


    If you would like to submit a bug report, please visit:

    opened by jinmfeng 0
  • v1.6.2(Aug 23, 2022)

    This is a patch release for bug fixes.

    • Remove pyarrow workaround. (#7884)
    • Fix monotone constraint with tuple input. (#7891)
    • Verify shared object version at load. (#7928)
    • Fix LTR with weighted Quantile DMatrix. (#7975)
    • Fix Python package source install. (#8036)
    • Limit max_depth to 30 for GPU. (#8098)
    • Fix compatibility with the latest cupy. (#8129)
    • [dask] Deterministic rank assignment. (#8018)
    • Fix loading DMatrix binary in distributed env. (#8149)
    Source code(tar.gz)
    Source code(zip)
  • v1.6.1(May 9, 2022)

    v1.6.1 (2022 May 9)

    This is a patch release for bug fixes and Spark barrier mode support. The R package is unchanged.

    Experimental support for categorical data

    • Fix segfault when the number of samples is smaller than the number of categories. (
    • Enable partition-based split for all model types. (

    JVM packages

    We replaced the old parallelism tracker with spark barrier mode to improve the robustness of the JVM package and fix the GPU training pipeline.

    • Fix GPU training pipeline quantile synchronization. (#7823, #7834)
    • Use barrier model in spark package. (,,,
    • Fix shared object loading on some platforms. (


    You can verify the downloaded packages by running this on your Unix shell:

    echo "<hash> <artifact>" | shasum -a 256 --check
    2633f15e7be402bad0660d270e0b9a84ad6fcfd1c690a5d454efd6d55b4e395b  ./xgboost.tar.gz
    Source code(tar.gz)
    Source code(zip)
    xgboost.tar.gz(2.54 MB)
  • v1.6.0(Apr 16, 2022)

    v1.6.0 (2022 Apr 16)

    After a long period of development, XGBoost v1.6.0 is packed with many new features and improvements. We summarize them in the following sections starting with an introduction to some major new features, then moving on to language binding specific changes including new features and notable bug fixes for that binding.

    Development of categorical data support

    This version of XGBoost features new improvements and full coverage of experimental categorical data support in Python and C package with tree model. Both hist, approx and gpu_hist now support training with categorical data. Also, partition-based categorical split is introduced in this release. This split type is first available in LightGBM in the context of gradient boosting. The previous XGBoost release supported one-hot split where the splitting criteria is of form x \in {c}, i.e. the categorical feature x is tested against a single candidate. The new release allows for more expressive conditions: x \in S where the categorical feature x is tested against multiple candidates. Moreover, it is now possible to use any tree algorithms (hist, approx, gpu_hist) when creating categorical splits. For more information, please see our tutorial on categorical data, along with examples linked on that page. (#7380, #7708, #7695, #7330, #7307, #7322, #7705, #7652, #7592, #7666, #7576, #7569, #7529, #7575, #7393, #7465, #7385, #7371, #7745, #7810)

    In the future, we will continue to improve categorical data support with new features and optimizations. Also, we are looking forward to bringing the feature beyond Python binding, contributions and feedback are welcomed! Lastly, as a result of experimental status, the behavior might be subject to change, especially the default value of related hyper-parameters.

    Experimental support for multi-output model

    XGBoost 1.6 features initial support for the multi-output model, which includes multi-output regression and multi-label classification. Along with this, the XGBoost classifier has proper support for base margin without to need for the user to flatten the input. In this initial support, XGBoost builds one model for each target similar to the sklearn meta estimator, for more details, please see our quick introduction.

    (#7365, #7736, #7607, #7574, #7521, #7514, #7456, #7453, #7455, #7434, #7429, #7405, #7381)

    External memory support

    External memory support for both approx and hist tree method is considered feature complete in XGBoost 1.6. Building upon the iterator-based interface introduced in the previous version, now both hist and approx iterates over each batch of data during training and prediction. In previous versions, hist concatenates all the batches into an internal representation, which is removed in this version. As a result, users can expect higher scalability in terms of data size but might experience lower performance due to disk IO. (#7531, #7320, #7638, #7372)

    Rewritten approx

    The approx tree method is rewritten based on the existing hist tree method. The rewrite closes the feature gap between approx and hist and improves the performance. Now the behavior of approx should be more aligned with hist and gpu_hist. Here is a list of user-visible changes:

    • Supports both max_leaves and max_depth.
    • Supports grow_policy.
    • Supports monotonic constraint.
    • Supports feature weights.
    • Use max_bin to replace sketch_eps.
    • Supports categorical data.
    • Faster performance for many of the datasets.
    • Improved performance and robustness for distributed training.
    • Supports prediction cache.
    • Significantly better performance for external memory when depthwise policy is used.

    New serialization format

    Based on the existing JSON serialization format, we introduce UBJSON support as a more efficient alternative. Both formats will be available in the future and we plan to gradually phase out support for the old binary model format. Users can opt to use the different formats in the serialization function by providing the file extension json or ubj. Also, the save_raw function in all supported languages bindings gains a new parameter for exporting the model in different formats, available options are json, ubj, and deprecated, see document for the language binding you are using for details. Lastly, the default internal serialization format is set to UBJSON, which affects Python pickle and R RDS. (#7572, #7570, #7358, #7571, #7556, #7549, #7416)

    General new features and improvements

    Aside from the major new features mentioned above, some others are summarized here:

    • Users can now access the build information of XGBoost binary in Python and C interface. (#7399, #7553)
    • Auto-configuration of seed_per_iteration is removed, now distributed training should generate closer results to single node training when sampling is used. (#7009)
    • A new parameter huber_slope is introduced for the Pseudo-Huber objective.
    • During source build, XGBoost can choose cub in the system path automatically. (#7579)
    • XGBoost now honors the CPU counts from CFS, which is usually set in docker environments. (#7654, #7704)
    • The metric aucpr is rewritten for better performance and GPU support. (#7297, #7368)
    • Metric calculation is now performed in double precision. (#7364)
    • XGBoost no longer mutates the global OpenMP thread limit. (#7537, #7519, #7608, #7590, #7589, #7588, #7687)
    • The default behavior of max_leave and max_depth is now unified (#7302, #7551).
    • CUDA fat binary is now compressed. (#7601)
    • Deterministic result for evaluation metric and linear model. In previous versions of XGBoost, evaluation results might differ slightly for each run due to parallel reduction for floating-point values, which is now addressed. (#7362, #7303, #7316, #7349)
    • XGBoost now uses double for GPU Hist node sum, which improves the accuracy of gpu_hist. (#7507)

    Performance improvements

    Most of the performance improvements are integrated into other refactors during feature developments. The approx should see significant performance gain for many datasets as mentioned in the previous section, while the hist tree method also enjoys improved performance with the removal of the internal pruner along with some other refactoring. Lastly, gpu_hist no longer synchronizes the device during training. (#7737)

    General bug fixes

    This section lists bug fixes that are not specific to any language binding.

    • The num_parallel_tree is now a model parameter instead of a training hyper-parameter, which fixes model IO with random forest. (#7751)
    • Fixes in CMake script for exporting configuration. (#7730)
    • XGBoost can now handle unsorted sparse input. This includes text file formats like libsvm and scipy sparse matrix where column index might not be sorted. (#7731)
    • Fix tree param feature type, this affects inputs with the number of columns greater than the maximum value of int32. (#7565)
    • Fix external memory with gpu_hist and subsampling. (#7481)
    • Check the number of trees in inplace predict, this avoids a potential segfault when an incorrect value for iteration_range is provided. (#7409)
    • Fix non-stable result in cox regression (#7756)

    Changes in the Python package

    Other than the changes in Dask, the XGBoost Python package gained some new features and improvements along with small bug fixes.

    • Python 3.7 is required as the lowest Python version. (#7682)
    • Pre-built binary wheel for Apple Silicon. (#7621, #7612, #7747) Apple Silicon users will now be able to run pip install xgboost to install XGBoost.
    • MacOS users no longer need to install libomp from Homebrew, as the XGBoost wheel now bundles libomp.dylib library.
    • There are new parameters for users to specify the custom metric with new behavior. XGBoost can now output transformed prediction values when a custom objective is not supplied. See our explanation in the tutorial for details.
    • For the sklearn interface, following the estimator guideline from scikit-learn, all parameters in fit that are not related to input data are moved into the constructor and can be set by set_params. (#6751, #7420, #7375, #7369)
    • Apache arrow format is now supported, which can bring better performance to users' pipeline (#7512)
    • Pandas nullable types are now supported (#7760)
    • A new function get_group is introduced for DMatrix to allow users to get the group information in the custom objective function. (#7564)
    • More training parameters are exposed in the sklearn interface instead of relying on the **kwargs. (#7629)
    • A new attribute feature_names_in_ is defined for all sklearn estimators like XGBRegressor to follow the convention of sklearn. (#7526)
    • More work on Python type hint. (#7432, #7348, #7338, #7513, #7707)
    • Support the latest pandas Index type. (#7595)
    • Fix for Feature shape mismatch error on s390x platform (#7715)
    • Fix using feature names for constraints with multiple groups (#7711)
    • We clarified the behavior of the callback function when it contains mutable states. (#7685)
    • Lastly, there are some code cleanups and maintenance work. (#7585, #7426, #7634, #7665, #7667, #7377, #7360, #7498, #7438, #7667, #7752, #7749, #7751)

    Changes in the Dask interface

    • Dask module now supports user-supplied host IP and port address of scheduler node. Please see introduction and API document for reference. (#7645, #7581)
    • Internal DMatrix construction in dask now honers thread configuration. (#7337)
    • A fix for nthread configuration using the Dask sklearn interface. (#7633)
    • The Dask interface can now handle empty partitions. An empty partition is different from an empty worker, the latter refers to the case when a worker has no partition of an input dataset, while the former refers to some partitions on a worker that has zero sizes. (#7644, #7510)
    • Scipy sparse matrix is supported as Dask array partition. (#7457)
    • Dask interface is no longer considered experimental. (#7509)

    Changes in the R package

    This section summarizes the new features, improvements, and bug fixes to the R package.

    • load.raw can optionally construct a booster as return. (#7686)
    • Fix parsing decision stump, which affects both transforming text representation to data table and plotting. (#7689)
    • Implement feature weights. (#7660)
    • Some improvements for complying the CRAN release policy. (#7672, #7661, #7763)
    • Support CSR data for predictions (#7615)
    • Document update (#7263, #7606)
    • New maintainer for the CRAN package (#7691, #7649)
    • Handle non-standard installation of toolchain on macos (#7759)

    Changes in JVM-packages

    Some new features for JVM-packages are introduced for a more integrated GPU pipeline and better compatibility with musl-based Linux. Aside from this, we have a few notable bug fixes.

    • User can specify the tracker IP address for training, which helps running XGBoost on restricted network environments. (#7808)
    • Add support for detecting musl-based Linux (#7624)
    • Add DeviceQuantileDMatrix to Scala binding (#7459)
    • Add Rapids plugin support, now more of the JVM pipeline can be accelerated by RAPIDS (#7491, #7779, #7793, #7806)
    • The setters for CPU and GPU are more aligned (#7692, #7798)
    • Control logging for early stopping (#7326)
    • Do not repartition when nWorker = 1 (#7676)
    • Fix the prediction issue for multi:softmax (#7694)
    • Fix for serialization of custom objective and eval (#7274)
    • Update documentation about Python tracker (#7396)
    • Remove jackson from dependency, which fixes CVE-2020-36518. (#7791)
    • Some refactoring to the training pipeline for better compatibility between CPU and GPU. (#7440, #7401, #7789, #7784)
    • Maintenance work. (#7550, #7335, #7641, #7523, #6792, #4676)


    Other than the changes in the Python package and serialization, we removed some deprecated features in previous releases. Also, as mentioned in the previous section, we plan to phase out the old binary format in future releases.

    • Remove old warning in 1.3 (#7279)
    • Remove label encoder deprecated in 1.3. (#7357)
    • Remove old callback deprecated in 1.3. (#7280)
    • Pre-built binary will no longer support deprecated CUDA architectures including sm35 and sm50. Users can continue to use these platforms with source build. (#7767)


    This section lists some of the general changes to XGBoost's document, for language binding specific change please visit related sections.

    • Document is overhauled to use the new RTD theme, along with integration of Python examples using Sphinx gallery. Also, we replaced most of the hard-coded URLs with sphinx references. (#7347, #7346, #7468, #7522, #7530)
    • Small update along with fixes for broken links, typos, etc. (#7684, #7324, #7334, #7655, #7628, #7623, #7487, #7532, #7500, #7341, #7648, #7311)
    • Update document for GPU. [skip ci] (#7403)
    • Document the status of RTD hosting. (#7353)
    • Update document for building from source. (#7664)
    • Add note about CRAN release [skip ci] (#7395)


    This is a summary of maintenance work that is not specific to any language binding.

    • Add CMake option to use /MD runtime (#7277)
    • Add clang-format configuration. (#7383)
    • Code cleanups (#7539, #7536, #7466, #7499, #7533, #7735, #7722, #7668, #7304, #7293, #7321, #7356, #7345, #7387, #7577, #7548, #7469, #7680, #7433, #7398)
    • Improved tests with better coverage and latest dependency (#7573, #7446, #7650, #7520, #7373, #7723, #7611, #7771)
    • Improved automation of the release process. (#7278, #7332, #7470)
    • Compiler workarounds (#7673)
    • Change shebang used in CLI demo. (#7389)
    • Update affiliation (#7289)


    Some fixes and update to XGBoost's CI infrastructure. (#7739, #7701, #7382, #7662, #7646, #7582, #7407, #7417, #7475, #7474, #7479, #7472, #7626)

    Source code(tar.gz)
    Source code(zip)
    xgboost.tar.gz(2.54 MB)
    xgboost_r_gpu_linux_1.6.0.tar.gz(94.00 MB)
    xgboost_r_gpu_win64_1.6.0.tar.gz(120.28 MB)
  • v1.6.0rc1(Mar 30, 2022)

  • v1.5.2(Jan 17, 2022)

    This is a patch release for compatibility with latest dependencies and bug fixes.

    • [dask] Fix asyncio with latest dask and distributed.
    • [R] Fix single sample SHAP prediction.
    • [Python] Update python classifier to indicate support for latest Python versions.
    • [Python] Fix with latest mypy and pylint.
    • Fix indexing type for bitfield, which may affect missing value and categorical data.
    • Fix num_boosted_rounds for linear model.
    • Fix early stopping with linear model.
    Source code(tar.gz)
    Source code(zip)
  • v1.5.1(Nov 23, 2021)

    This is a patch release for compatibility with the latest dependencies and bug fixes. Also, all GPU-compatible binaries are built with CUDA 11.0.

    • [Python] Handle missing values in dataframe with category dtype. (#7331)

    • [R] Fix R CRAN failures about prediction and some compiler warnings.

    • [JVM packages] Fix compatibility with latest Spark (#7438, #7376)

    • Support building with CTK11.5. (#7379)

    • Check user input for iteration in inplace predict.

    • Handle OMP_THREAD_LIMIT environment variable.

    • [doc] Fix broken links. (#7341)


    You can verify the downloaded packages by running this on your Unix shell:

    echo "<hash> <artifact>" | shasum -a 256 --check
    3a6cc7526c0dff1186f01b53dcbac5c58f12781988400e2d340dda61ef8d14ca  xgboost_r_gpu_linux_afb9dfd4210e8b8db8fe03380f83b404b1721443.tar.gz
    6f74deb62776f1e2fd030e1fa08b93ba95b32ac69cc4096b4bcec3821dd0a480  xgboost_r_gpu_win64_afb9dfd4210e8b8db8fe03380f83b404b1721443.tar.gz
    565dea0320ed4b6f807dbb92a8a57e86ec16db50eff9a3f405c651d1f53a259d  xgboost.tar.gz
    Source code(tar.gz)
    Source code(zip)
    xgboost.tar.gz(2.29 MB)
    xgboost_r_gpu_linux_afb9dfd4210e8b8db8fe03380f83b404b1721443.tar.gz(80.41 MB)
    xgboost_r_gpu_win64_afb9dfd4210e8b8db8fe03380f83b404b1721443.tar.gz(100.50 MB)
  • v1.5.0(Oct 17, 2021)

    This release comes with many exciting new features and optimizations, along with some bug fixes. We will describe the experimental categorical data support and the external memory interface independently. Package-specific new features will be listed in respective sections.

    Development on categorical data support

    In version 1.3, XGBoost introduced an experimental feature for handling categorical data natively, without one-hot encoding. XGBoost can fit categorical splits in decision trees. (Currently, the generated splits will be of form x \in {v}, where the input is compared to a single category value. A future version of XGBoost will generate splits that compare the input against a list of multiple category values.)

    Most of the other features, including prediction, SHAP value computation, feature importance, and model plotting were revised to natively handle categorical splits. Also, all Python interfaces including native interface with and without quantized DMatrix, scikit-learn interface, and Dask interface now accept categorical data with a wide range of data structures support including numpy/cupy array and cuDF/pandas/modin dataframe. In practice, the following are required for enabling categorical data support during training:

    • Use Python package.
    • Use gpu_hist to train the model.
    • Use JSON model file format for saving the model.

    Once the model is trained, it can be used with most of the features that are available on the Python package. For a quick introduction, see

    Related PRs: (#7011, #7001, #7042, #7041, #7047, #7043, #7036, #7054, #7053, #7065, #7213, #7228, #7220, #7221, #7231, #7306)

    • Next steps

      • Revise the CPU training algorithm to handle categorical data natively and generate categorical splits
      • Extend the CPU and GPU algorithms to generate categorical splits of form x \in S where the input is compared with multiple category values. split. (#7081)

    External memory

    This release features a brand-new interface and implementation for external memory (also known as out-of-core training). (#6901, #7064, #7088, #7089, #7087, #7092, #7070, #7216). The new implementation leverages the data iterator interface, which is currently used to create DeviceQuantileDMatrix. For a quick introduction, see . During the development of this new interface, lz4 compression is removed. (#7076). Please note that external memory support is still experimental and not ready for production use yet. All future development will focus on this new interface and users are advised to migrate. (You are using the old interface if you are using a URL suffix to use external memory.)

    New features in Python package

    • Support numpy array interface and all numeric types from numpy in DMatrix construction and inplace_predict (#6998, #7003). Now XGBoost no longer makes data copy when input is numpy array view.
    • The early stopping callback in Python has a new min_delta parameter to control the stopping behavior (#7137)
    • Python package now supports calculating feature scores for the linear model, which is also available on R package. (#7048)
    • Python interface now supports configuring constraints using feature names instead of feature indices.
    • Typehint support for more Python code including scikit-learn interface and rabit module. (#6799, #7240)
    • Add tutorial for XGBoost-Ray (#6884)

    New features in R package

    • In 1.4 we have a new prediction function in the C API which is used by the Python package. This release revises the R package to use the new prediction function as well. A new parameter iteration_range for the predict function is available, which can be used for specifying the range of trees for running prediction. (#6819, #7126)
    • R package now supports the nthread parameter in DMatrix construction. (#7127)

    New features in JVM packages

    • Support GPU dataframe and DeviceQuantileDMatrix (#7195). Constructing DMatrix with GPU data structures and the interface for quantized DMatrix were first introduced in the Python package and are now available in the xgboost4j package.
    • JVM packages now support saving and getting early stopping attributes. (#7095) Here is a quick example in JAVA (#7252).

    General new features

    • We now have a pre-built binary package for R on Windows with GPU support. (#7185)
    • CUDA compute capability 86 is now part of the default CMake build configuration with newly added support for CUDA 11.4. (#7131, #7182, #7254)
    • XGBoost can be compiled using system CUB provided by CUDA 11.x installation. (#7232)


    The performance for both hist and gpu_hist has been significantly improved in 1.5 with the following optimizations:

    • GPU multi-class model training now supports prediction cache. (#6860)
    • GPU histogram building is sped up and the overall training time is 2-3 times faster on large datasets (#7180, #7198). In addition, we removed the parameter deterministic_histogram and now the GPU algorithm is always deterministic.
    • CPU hist has an optimized procedure for data sampling (#6922)
    • More performance optimization in regression and binary classification objectives on CPU (#7206)
    • Tree model dump is now performed in parallel (#7040)

    Breaking changes

    • n_gpus was deprecated in 1.0 release and is now removed.
    • Feature grouping in CPU hist tree method is removed, which was disabled long ago. (#7018)
    • C API for Quantile DMatrix is changed to be consistent with the new external memory implementation. (#7082)

    Notable general bug fixes

    • XGBoost no long changes global CUDA device ordinal when gpu_id is specified (#6891, #6987)
    • Fix gamma negative likelihood evaluation metric. (#7275)
    • Fix integer value of verbose_eal for function in Python. (#7291)
    • Remove extra sync in CPU hist for dense data, which can lead to incorrect tree node statistics. (#7120, #7128)
    • Fix a bug in GPU hist when data size is larger than UINT32_MAX with missing values. (#7026)
    • Fix a thread safety issue in prediction with the softmax objective. (#7104)
    • Fix a thread safety issue in CPU SHAP value computation. (#7050) Please note that all prediction functions in Python are thread-safe.
    • Fix model slicing. (#7149, #7078)
    • Workaround a bug in old GCC which can lead to segfault during construction of DMatrix. (#7161)
    • Fix histogram truncation in GPU hist, which can lead to slightly-off results. (#7181)
    • Fix loading GPU linear model pickle files on CPU-only machine. (#7154)
    • Check input value is duplicated when CPU quantile queue is full (#7091)
    • Fix parameter loading with training continuation. (#7121)
    • Fix CMake interface for exposing C library by specifying dependencies. (#7099)
    • Callback and early stopping are explicitly disabled for the scikit-learn interface random forest estimator. (#7236)
    • Fix compilation error on x86 (32-bit machine) (#6964)
    • Fix CPU memory usage with extremely sparse datasets (#7255)
    • Fix a bug in GPU multi-class AUC implementation with weighted data (#7300)

    Python package

    Other than the items mentioned in the previous sections, there are some Python-specific improvements.

    • Change development release postfix to dev (#6988)
    • Fix early stopping behavior with MAPE metric (#7061)
    • Fixed incorrect feature mismatch error message (#6949)
    • Add predictor to skl constructor. (#7000, #7159)
    • Re-enable feature validation in predict proba. (#7177)
    • scikit learn interface regression estimator now can pass the scikit-learn estimator check and is fully compatible with scikit-learn utilities. __sklearn_is_fitted__ is implemented as part of the changes (#7130, #7230)
    • Conform the latest pylint. (#7071, #7241)
    • Support latest panda range index in DMatrix construction. (#7074)
    • Fix DMatrix construction from pandas series. (#7243)
    • Fix typo and grammatical mistake in error message (#7134)
    • [dask] disable work stealing explicitly for training tasks (#6794)
    • [dask] Set dataframe index in predict. (#6944)
    • [dask] Fix prediction on df with latest dask. (#6969)
    • [dask] Fix dask predict on DaskDMatrix with iteration_range. (#7005)
    • [dask] Disallow importing non-dask estimators from xgboost.dask (#7133)

    R package

    Improvements other than new features on R package:

    • Optimization for updating R handles in-place (#6903)
    • Removed the magrittr dependency. (#6855, #6906, #6928)
    • The R package now hides all C++ symbols to avoid conflicts. (#7245)
    • Other maintenance including code cleanups, document updates. (#6863, #6915, #6930, #6966, #6967)

    JVM packages

    Improvements other than new features on JVM packages:

    • Constructors with implicit missing value are deprecated due to confusing behaviors. (#7225)
    • Reduce scala-compiler, scalatest dependency scopes (#6730)
    • Making the Java library loader emit helpful error messages on missing dependencies. (#6926)
    • JVM packages now use the Python tracker in XGBoost instead of dmlc. The one in XGBoost is shared between JVM packages and Python Dask and enjoys better maintenance (#7132)
    • Fix "key not found: train" error (#6842)
    • Fix model loading from stream (#7067)

    General document improvements

    • Overhaul the installation documents. (#6877)
    • A few demos are added for AFT with dask (#6853), callback with dask (#6995), inference in C (#7151), process_type. (#7135)
    • Fix PDF format of document. (#7143)
    • Clarify the behavior of use_rmm. (#6808)
    • Clarify prediction function. (#6813)
    • Improve tutorial on feature interactions (#7219)
    • Add small example for dask sklearn interface. (#6970)
    • Update Python intro. (#7235)
    • Some fixes/updates (#6810, #6856, #6935, #6948, #6976, #7084, #7097, #7170, #7173, #7174, #7226, #6979, #6809, #6796, #6979)


    • Some refactoring around CPU hist, which lead to better performance but are listed under general maintenance tasks:

      • Extract evaluate splits from CPU hist. (#7079)
      • Merge lossgude and depthwise strategies for CPU hist (#7007)
      • Simplify sparse and dense CPU hist kernels (#7029)
      • Extract histogram builder from CPU Hist. (#7152)
    • Others

      • Fix gpu_id with custom objective. (#7015)
      • Fix typos in AUC. (#6795)
      • Use constexpr in dh::CopyIf. (#6828)
      • Update dmlc-core. (#6862)
      • Bump version to 1.5.0 snapshot in master. (#6875)
      • Relax shotgun test. (#6900)
      • Guard against index error in prediction. (#6982)
      • Hide symbols in CI build + hide symbols for C and CUDA (#6798)
      • Persist data in dask test. (#7077)
      • Fix typo in arguments of PartitionBuilder::Init (#7113)
      • Fix typo in src/common/ BuildHistKernel (#7116)
      • Use upstream URI in distributed quantile tests. (#7129)
      • Include cpack (#7160)
      • Remove synchronization in monitor. (#7164)
      • Remove unused code. (#7175)
      • Fix building on CUDA 11.0. (#7187)
      • Better error message for ncclUnhandledCudaError. (#7190)
      • Add noexcept to JSON objects. (#7205)
      • Improve wording for warning (#7248)
      • Fix typo in release script. [skip ci] (#7238)
      • Relax shotgun test. (#6918)
      • Relax test for decision stump in distributed environment. (#6919)
      • [dask] speed up tests (#7020)


    • [CI] Rotate access keys for uploading MacOS artifacts from Travis CI (#7253)
    • Reduce Travis environment setup time. (#6912)
    • Restore R cache on github action. (#6985)
    • [CI] Remove stray build artifact to avoid error in artifact packaging (#6994)
    • [CI] Move appveyor tests to action (#6986)
    • Remove appveyor badge. [skip ci] (#7035)
    • [CI] Configure RAPIDS, dask, modin (#7033)
    • Test on s390x. (#7038)
    • [CI] Upgrade to CMake 3.14 (#7060)
    • [CI] Update R cache. (#7102)
    • [CI] Pin libomp to 11.1.0 (#7107)
    • [CI] Upgrade build image to CentOS 7 + GCC 8; require CUDA 10.1 and later (#7141)
    • [dask] Work around segfault in prediction. (#7112)
    • [dask] Remove the workaround for segfault. (#7146)
    • [CI] Fix hanging Python setup in Windows CI (#7186)
    • [CI] Clean up in beginning of each task in Win CI (#7189)
    • Fix travis. (#7237)


    • Contributors: Adam Pocock (@Craigacp), Jeff H (@JeffHCross), Johan Hansson (@JohanWork), Jose Manuel Llorens (@JoseLlorensRipolles), Benjamin Szőke (@Livius90), @ReeceGoding, @ShvetsKS, Robert Zabel (@ZabelTech), Ali (@ali5h), Andrew Ziem (@az0), Andy Adinets (@canonizer), @david-cortes, Daniel Saxton (@dsaxton), Emil Sadek (@esadek), @farfarawayzyt, Gil Forsyth (@gforsyth), @giladmaya, @graue70, Philip Hyunsu Cho (@hcho3), James Lamb (@jameslamb), José Morales (@jmoralez), Kai Fricke (@krfricke), Christian Lorentzen (@lorentzenchr), Mads R. B. Kristensen (@madsbk), Anton Kostin (@masguit42), Martin Petříček (@mpetricek-corp), @naveenkb, Taewoo Kim (@oOTWK), Viktor Szathmáry (@phraktle), Robert Maynard (@robertmaynard), TP Boudreau (@tpboudreau), Jiaming Yuan (@trivialfis), Paul Taylor (@trxcllnt), @vslaykovsky, Bobby Wang (@wbo4958),
    • Reviewers: Nan Zhu (@CodingCat), Adam Pocock (@Craigacp), Jose Manuel Llorens (@JoseLlorensRipolles), Kodi Arfer (@Kodiologist), Benjamin Szőke (@Livius90), Mark Guryanov (@MarkGuryanov), Rory Mitchell (@RAMitchell), @ReeceGoding, @ShvetsKS, Egor Smirnov (@SmirnovEgorRu), Andrew Ziem (@az0), @candalfigomoro, Andy Adinets (@canonizer), Dante Gama Dessavre (@dantegd), @david-cortes, Daniel Saxton (@dsaxton), @farfarawayzyt, Gil Forsyth (@gforsyth), Harutaka Kawamura (@harupy), Philip Hyunsu Cho (@hcho3), @jakirkham, James Lamb (@jameslamb), José Morales (@jmoralez), James Bourbeau (@jrbourbeau), Christian Lorentzen (@lorentzenchr), Martin Petříček (@mpetricek-corp), Nikolay Petrov (@napetrov), @naveenkb, Viktor Szathmáry (@phraktle), Robin Teuwens (@rteuwens), Yuan Tang (@terrytangyuan), TP Boudreau (@tpboudreau), Jiaming Yuan (@trivialfis), @vkuzmin-uber, Bobby Wang (@wbo4958), William Hicks (@wphicks)


    You can verify the downloaded packages by running this on your unix shell:

    echo "<hash> <artifact>" | shasum -a 256 --check
    2c63e8abd3e89795ac9371688daa31109a9514eebd9db06956ba5aa41d0c0e20  xgboost_r_gpu_linux_1.5.0.tar.gz
    8b19f817dcb6b601b0abffa9cf943ee92c3e9a00f56fa3f4fcdfe98cd3777c04  xgboost_r_gpu_win64_1.5.0.tar.gz
    25ee3adb9925d0529575c0f00a55ba42202a1cdb5fdd3fb6484b4088571326a5  xgboost.tar.gz
    Source code(tar.gz)
    Source code(zip)
    xgboost.tar.gz(2.26 MB)
    xgboost_r_gpu_linux_1.5.0.tar.gz(80.41 MB)
    xgboost_r_gpu_win64_1.5.0.tar.gz(100.50 MB)
  • v1.5.0rc1(Sep 26, 2021)

  • v1.4.2(May 13, 2021)

    This is a patch release for Python package with following fixes:

    • Handle the latest version of cupy.ndarray in inplace_predict.
    • Ensure output array from predict_leaf is (n_samples, ) when there's only 1 tree. 1.4.0 outputs (n_samples, 1).
    • Fix empty dataset handling with multi-class AUC.
    • Handle object type from pandas in inplace_predict.

    You can verify the downloaded source code xgboost.tar.gz by running this on your unix shell:

    echo "3ffd4a90cd03efde596e51cadf7f344c8b6c91aefd06cc92db349cd47056c05a *xgboost.tar.gz" | shasum -a 256 --check
    Source code(tar.gz)
    Source code(zip)
    xgboost.tar.gz(2.20 MB)
  • v1.4.1(Apr 20, 2021)

  • v1.4.0(Apr 11, 2021)

    Introduction of pre-built binary package for R, with GPU support

    Starting with release 1.4.0, users now have the option of installing {xgboost} without having to build it from the source. This is particularly advantageous for users who want to take advantage of the GPU algorithm (gpu_hist), as previously they'd have to build {xgboost} from the source using CMake and NVCC. Now installing {xgboost} with GPU support is as easy as: R CMD INSTALL ./xgboost_r_gpu_linux.tar.gz. (#6827)

    See the instructions at

    Improvements on prediction functions

    XGBoost has many prediction types including shap value computation and inplace prediction. In 1.4 we overhauled the underlying prediction functions for C API and Python API with an unified interface. (#6777, #6693, #6653, #6662, #6648, #6668, #6804)

    • Starting with 1.4, sklearn interface prediction will use inplace predict by default when input data is supported.
    • Users can use inplace predict with dart booster and enable GPU acceleration just like gbtree.
    • Also all prediction functions with tree models are now thread-safe. Inplace predict is improved with base_margin support.
    • A new set of C predict functions are exposed in the public interface.
    • A user-visible change is a newly added parameter called strict_shape. See for more details.

    Improvement on Dask interface

    • Starting with 1.4, the Dask interface is considered to be feature-complete, which means all of the models found in the single node Python interface are now supported in Dask, including but not limited to ranking and random forest. Also, the prediction function is significantly faster and supports shap value computation.

      • Most of the parameters found in single node sklearn interface are supported by Dask interface. (#6471, #6591)
      • Implements learning to rank. On the Dask interface, we use the newly added support of query ID to enable group structure. (#6576)
      • The Dask interface has Python type hints support. (#6519)
      • All models can be safely pickled. (#6651)
      • Random forest estimators are now supported. (#6602)
      • Shap value computation is now supported. (#6575, #6645, #6614)
      • Evaluation result is printed on the scheduler process. (#6609)
      • DaskDMatrix (and device quantile dmatrix) now accepts all meta-information. (#6601)
    • Prediction optimization. We enhanced and speeded up the prediction function for the Dask interface. See the latest Dask tutorial page in our document for an overview of how you can optimize it even further. (#6650, #6645, #6648, #6668)

    • Bug fixes

      • If you are using the latest Dask and distributed where distributed.MultiLock is present, XGBoost supports training multiple models on the same cluster in parallel. (#6743)
      • A bug fix for when using dask.client to launch async task, XGBoost might use a different client object internally. (#6722)
    • Other improvements on documents, blogs, tutorials, and demos. (#6389, #6366, #6687, #6699, #6532, #6501)

    Python package

    With changes from Dask and general improvement on prediction, we have made some enhancements on the general Python interface and IO for booster information. Starting from 1.4, booster feature names and types can be saved into the JSON model. Also some model attributes like best_iteration, best_score are restored upon model load. On sklearn interface, some attributes are now implemented as Python object property with better documents.

    • Breaking change: All data parameters in prediction functions are renamed to X for better compliance to sklearn estimator interface guidelines.

    • Breaking change: XGBoost used to generate some pseudo feature names with DMatrix when inputs like np.ndarray don't have column names. The procedure is removed to avoid conflict with other inputs. (#6605)

    • Early stopping with training continuation is now supported. (#6506)

    • Optional import for Dask and cuDF are now lazy. (#6522)

    • As mentioned in the prediction improvement summary, the sklearn interface uses inplace prediction whenever possible. (#6718)

    • Booster information like feature names and feature types are now saved into the JSON model file. (#6605)

    • All DMatrix interfaces including DeviceQuantileDMatrix and counterparts in Dask interface (as mentioned in the Dask changes summary) now accept all the meta-information like group and qid in their constructor for better consistency. (#6601)

    • Booster attributes are restored upon model load so users don't have to call attr manually. (#6593)

    • On sklearn interface, all models accept base_margin for evaluation datasets. (#6591)

    • Improvements over the setup script including smaller sdist size and faster installation if the C++ library is already built (#6611, #6694, #6565).

    • Bug fixes for Python package:

      • Don't validate feature when number of rows is 0. (#6472)
      • Move metric configuration into booster. (#6504)
      • Calling should clear the Booster by default (#6562)
      • Support _estimator_type. (#6582)
      • [dask, sklearn] Fix predict proba. (#6566, #6817)
      • Restore unknown data support. (#6595)
      • Fix learning rate scheduler with cv. (#6720)
      • Fixes small typo in sklearn documentation (#6717)
      • [python-package] Fix class Booster: feature_types = None (#6705)
      • Fix divide by 0 in feature importance when no split is found. (#6676)

    JVM package

    • [jvm-packages] fix early stopping doesn't work even without custom_eval setting (#6738)
    • fix potential TaskFailedListener's callback won't be called (#6612)
    • [jvm] Add ability to load booster direct from byte array (#6655)
    • [jvm-packages] JVM library loader extensions (#6630)

    R package

    • R documentation: Make construction of DMatrix consistent.
    • Fix R documentation for xgb.train. (#6764)


    We re-implemented the ROC-AUC metric in XGBoost. The new implementation supports multi-class classification and has better support for learning to rank tasks that are not binary. Also, it has a better-defined average on distributed environments with additional handling for invalid datasets. (#6749, #6747, #6797)

    Global configuration.

    Starting from 1.4, XGBoost's Python, R and C interfaces support a new global configuration model where users can specify some global parameters. Currently, supported parameters are verbosity and use_rmm. The latter is experimental, see rmm plugin demo and related README file for details. (#6414, #6656)

    Other New features.

    • Better handling for input data types that support __array_interface__. For some data types including GPU inputs and scipy.sparse.csr_matrix, XGBoost employs __array_interface__ for processing the underlying data. Starting from 1.4, XGBoost can accept arbitrary array strides (which means column-major is supported) without making data copies, potentially reducing a significant amount of memory consumption. Also version 3 of __cuda_array_interface__ is now supported. (#6776, #6765, #6459, #6675)
    • Improved parameter validation, now feeding XGBoost with parameters that contain whitespace will trigger an error. (#6769)
    • For Python and R packages, file paths containing the home indicator ~ are supported.
    • As mentioned in the Python changes summary, the JSON model can now save feature information of the trained booster. The JSON schema is updated accordingly. (#6605)
    • Development of categorical data support is continued. Newly added weighted data support and dart booster support. (#6508, #6693)
    • As mentioned in Dask change summary, ranking now supports the qid parameter for query groups. (#6576)
    • DMatrix.slice can now consume a numpy array. (#6368)

    Other breaking changes

    • Aside from the feature name generation, there are 2 breaking changes:
      • Drop saving binary format for memory snapshot. (#6513, #6640)
      • Change default evaluation metric for binary:logitraw objective to logloss (#6647)

    CPU Optimization

    • Aside from the general changes on predict function, some optimizations are applied on CPU implementation. (#6683, #6550, #6696, #6700)
    • Also performance for sampling initialization in hist is improved. (#6410)

    Notable fixes in the core library

    These fixes do not reside in particular language bindings:

    • Fixes for gamma regression. This includes checking for invalid input values, fixes for gamma deviance metric, and better floating point guard for gamma negative log-likelihood metric. (#6778, #6537, #6761)
    • Random forest with gpu_hist might generate low accuracy in previous versions. (#6755)
    • Fix a bug in GPU sketching when data size exceeds limit of 32-bit integer. (#6826)
    • Memory consumption fix for row-major adapters (#6779)
    • Don't estimate sketch batch size when rmm is used. (#6807) (#6830)
    • Fix in-place predict with missing value. (#6787)
    • Re-introduce double buffer in UpdatePosition, to fix perf regression in gpu_hist (#6757)
    • Pass correct split_type to GPU predictor (#6491)
    • Fix DMatrix feature names/types IO. (#6507)
    • Use view for SparsePage exclusively to avoid some data access races. (#6590)
    • Check for invalid data. (#6742)
    • Fix relocatable include in CMakeList (#6734) (#6737)
    • Fix DMatrix slice with feature types. (#6689)

    Other deprecation notices:

    • This release will be the last release to support CUDA 10.0. (#6642)

    • Starting in the next release, the Python package will require Pip 19.3+ due to the use of manylinux2014 tag. Also, CentOS 6, RHEL 6 and other old distributions will not be supported.

    Known issue:

    MacOS build of the JVM packages doesn't support multi-threading out of the box. To enable multi-threading with JVM packages, MacOS users will need to build the JVM packages from the source. See


    • Dedicated page for tree_method parameter is added. (#6564, #6633)
    • [doc] Add FLAML as a fast tuning tool for XGBoost (#6770)
    • Add document for tests directory. [skip ci] (#6760)
    • Fix doc string of to use correct versionadded (#6458)
    • Update demo for prediction. (#6789)
    • [Doc] Document that AUCPR is for binary classification/ranking (#5899)
    • Update the C API comments (#6457)
    • Fix document. [skip ci] (#6669)

    Maintenance: Testing, continuous integration

    • Use CPU input for test_boost_from_prediction. (#6818)
    • [CI] Upload xgboost4j.dll to S3 (#6781)
    • Update dmlc-core submodule (#6745)
    • [CI] Use manylinux2010_x86_64 container to vendor libgomp (#6485)
    • Add conda-forge badge (#6502)
    • Fix merge conflict. (#6512)
    • [CI] Split up main.yml, add mypy. (#6515)
    • [Breaking] Upgrade cuDF and RMM to 0.18 nightlies; require RMM 0.18+ for RMM plugin (#6510)
    • "featue_map" typo changed to "feature_map" (#6540)
    • Add script for generating release tarball. (#6544)
    • Add credentials to .gitignore (#6559)
    • Remove warnings in tests. (#6554)
    • Update dmlc-core submodule and conform to new API (#6431)
    • Suppress hypothesis health check for dask client. (#6589)
    • Fix pylint. (#6714)
    • [CI] Clear R package cache (#6746)
    • Exclude dmlc test on github action. (#6625)
    • Tests for regression metrics with weights. (#6729)
    • Add helper script and doc for releasing pip package. (#6613)
    • Support pylint 2.7.0 (#6726)
    • Remove R cache in github action. (#6695)
    • [CI] Do not mix up stashed executable built for ARM and x86_64 platforms (#6646)
    • [CI] Add ARM64 test to Jenkins pipeline (#6643)
    • Disable s390x and arm64 tests on travis for now. (#6641)
    • Move sdist test to action. (#6635)
    • [dask] Rework base margin test. (#6627)

    Maintenance: Refactor code for legibility and maintainability

    • Improve OpenMP exception handling (#6680)
    • Improve string view to reduce string allocation. (#6644)
    • Simplify Span checks. (#6685)
    • Use generic dispatching routine for array interface. (#6672)

    You can verify the downloaded source code xgboost.tar.gz by running this on your unix shell:

    echo "ff77130a86aebd83a8b996c76768a867b0a6e5012cce89212afc3df4c4ee6b1c *xgboost.tar.gz" | shasum -a 256 --check
    Source code(tar.gz)
    Source code(zip)
    xgboost.tar.gz(2.20 MB)
    xgboost_r_gpu_linux_1.4.0.tar.gz(74.32 MB)
  • v1.3.3(Jan 20, 2021)

  • v1.3.2(Jan 13, 2021)

    • Fix compatibility with newer scikit-learn. (
    • Fix wrong best_ntree_limit in multi-class. (
    • Ensure that Rabit can be compiled on Solaris (
    • Fix best_ntree_limit for linear and dart. (
    • Remove duplicated DMatrix creation in scikit-learn interface. (
    • Fix evals_result in XGBRanker. (#
    Source code(tar.gz)
    Source code(zip)
  • v1.3.1(Dec 22, 2020)

    • Enable loading model from <1.0.0 trained with objective='binary:logitraw' (#6517)
    • Fix handling of print period in EvaluationMonitor (#6499)
    • Fix a bug in metric configuration after loading model. (#6504)
    • Fix save_best early stopping option (#6523)
    • Remove cupy.array_equal, since it's not compatible with cuPy 7.8 (#6528)

    You can verify the downloaded source code xgboost.tar.gz by running this on your unix shell:

    echo "fd51e844dd0291fd9e7129407be85aaeeda2309381a6e3fc104938b27fb09279 *xgboost.tar.gz" | shasum -a 256 --check
    Source code(tar.gz)
    Source code(zip)
    xgboost.tar.gz(2.13 MB)
  • v1.3.0(Dec 9, 2020)

    XGBoost4J-Spark: Exceptions should cancel jobs gracefully instead of killing SparkContext (#6019).

    • By default, exceptions in XGBoost4J-Spark causes the whole SparkContext to shut down, necessitating the restart of the Spark cluster. This behavior is often a major inconvenience.
    • Starting from 1.3.0 release, XGBoost adds a new parameter killSparkContextOnWorkerFailure to optionally prevent killing SparkContext. If this parameter is set, exceptions will gracefully cancel training jobs instead of killing SparkContext.

    GPUTreeSHAP: GPU acceleration of the TreeSHAP algorithm (#6038, #6064, #6087, #6099, #6163, #6281, #6332)

    • SHAP (SHapley Additive exPlanations) is a game theoretic approach to explain predictions of machine learning models. It computes feature importance scores for individual examples, establishing how each feature influences a particular prediction. TreeSHAP is an optimized SHAP algorithm specifically designed for decision tree ensembles.
    • Starting with 1.3.0 release, it is now possible to leverage CUDA-capable GPUs to accelerate the TreeSHAP algorithm. Check out the demo notebook.
    • The CUDA implementation of the TreeSHAP algorithm is hosted at rapidsai/GPUTreeSHAP. XGBoost imports it as a Git submodule.

    New style Python callback API (#6199, #6270, #6320, #6348, #6376, #6399, #6441)

    • The XGBoost Python package now offers a re-designed callback API. The new callback API lets you design various extensions of training in idomatic Python. In addition, the new callback API allows you to use early stopping with the native Dask API (xgboost.dask). Check out the tutorial and the demo.

    Enable the use of DeviceQuantileDMatrix / DaskDeviceQuantileDMatrix with large data (#6201, #6229, #6234).

    • DeviceQuantileDMatrix can achieve memory saving by avoiding extra copies of the training data, and the saving is bigger for large data. Unfortunately, large data with more than 2^31 elements was triggering integer overflow bugs in CUB and Thrust. Tracking issue: #6228.
    • This release contains a series of work-arounds to allow the use of DeviceQuantileDMatrix with large data:
      • Loop over copy_if (#6201)
      • Loop over thrust::reduce (#6229)
      • Implement the inclusive scan algorithm in-house, to handle large offsets (#6234)

    Support slicing of tree models (#6302)

    • Accessing the best iteration of a model after the application of early stopping used to be error-prone, need to manually pass the ntree_limit argument to the predict() function.
    • Now we provide a simple interface to slice tree models by specifying a range of boosting rounds. The tree ensemble can be split into multiple sub-ensembles via the slicing interface. Check out an example.
    • In addition, the early stopping callback now supports save_best option. When enabled, XGBoost will save (persist) the model at the best boosting round and discard the trees that were fit subsequent to the best round.

    Weighted subsampling of features (columns) (#5962)

    • It is now possible to sample features (columns) via weighted subsampling, in which features with higher weights are more likely to be selected in the sample. Weighted subsampling allows you to encode domain knowledge by emphasizing a particular set of features in the choice of tree splits. In addition, you can prevent particular features from being used in any splits, by assigning them zero weights.
    • Check out the demo.

    Improved integration with Dask

    • Support reverse-proxy environment such as Google Kubernetes Engine (#6343, #6475)
    • An XGBoost training job will no longer use all available workers. Instead, it will only use the workers that contain input data (#6343).
    • The new callback API works well with the Dask training API.
    • The predict() and fit() function of DaskXGBClassifier and DaskXGBRegressor now accept a base margin (#6155).
    • Support more meta data in the Dask API (#6130, #6132, #6333).
    • Allow passing extra keyword arguments as kwargs in predict() (#6117)
    • Fix typo in dask interface: sample_weights -> sample_weight (#6240)
    • Allow empty data matrix in AFT survival, as Dask may produce empty partitions (#6379)
    • Speed up prediction by overlapping prediction jobs in all workers (#6412)

    Experimental support for direct splits with categorical features (#6028, #6128, #6137, #6140, #6164, #6165, #6166, #6179, #6194, #6219)

    • Currently, XGBoost requires users to one-hot-encode categorical variables. This has adverse performance implications, as the creation of many dummy variables results into higher memory consumption and may require fitting deeper trees to achieve equivalent model accuracy.
    • The 1.3.0 release of XGBoost contains an experimental support for direct handling of categorical variables in test nodes. Each test node will have the condition of form feature_value \in match_set, where the match_set on the right hand side contains one or more matching categories. The matching categories in match_set represent the condition for traversing to the right child node. Currently, XGBoost will only generate categorical splits with only a single matching category ("one-vs-rest split"). In a future release, we plan to remove this restriction and produce splits with multiple matching categories in match_set.
    • The categorical split requires the use of JSON model serialization. The legacy binary serialization method cannot be used to save (persist) models with categorical splits.
    • Note. This feature is currently highly experimental. Use it at your own risk. See the detailed list of limitations at #5949.

    Experimental plugin for RAPIDS Memory Manager (#5873, #6131, #6146, #6150, #6182)

    • RAPIDS Memory Manager library (rapidsai/rmm) provides a collection of efficient memory allocators for NVIDIA GPUs. It is now possible to use XGBoost with memory allocators provided by RMM, by enabling the RMM integration plugin. With this plugin, XGBoost is now able to share a common GPU memory pool with other applications using RMM, such as the RAPIDS data science packages.
    • See the demo for a working example, as well as directions for building XGBoost with the RMM plugin.
    • The plugin will be soon considered non-experimental, once #6297 is resolved.

    Experimental plugin for oneAPI programming model (#5825)

    • oneAPI is a programming interface developed by Intel aimed at providing one programming model for many types of hardware such as CPU, GPU, FGPA and other hardware accelerators.
    • XGBoost now includes an experimental plugin for using oneAPI for the predictor and objective functions. The plugin is hosted in the directory plugin/updater_oneapi.
    • Roadmap: #5442

    Pickling the XGBoost model will now trigger JSON serialization (#6027)

    • The pickle will now contain the JSON string representation of the XGBoost model, as well as related configuration.

    Performance improvements

    • Various performance improvement on multi-core CPUs
      • Optimize DMatrix build time by up to 3.7x. (#5877)
      • CPU predict performance improvement, by up to 3.6x. (#6127)
      • Optimize CPU sketch allreduce for sparse data (#6009)
      • Thread local memory allocation for BuildHist, leading to speedup up to 1.7x. (#6358)
      • Disable hyperthreading for DMatrix creation (#6386). This speeds up DMatrix creation by up to 2x.
      • Simple fix for static shedule in predict (#6357)
    • Unify thread configuration, to make it easy to utilize all CPU cores (#6186)
    • [jvm-packages] Clean the way deterministic paritioning is computed (#6033)
    • Speed up JSON serialization by implementing an intrusive pointer class (#6129). It leads to 1.5x-2x performance boost.

    API additions

    • [R] Add SHAP summary plot using ggplot2 (#5882)
    • Modin DataFrame can now be used as input (#6055)
    • [jvm-packages] Add getNumFeature method (#6075)
    • Add MAPE metric (#6119)
    • Implement GPU predict leaf. (#6187)
    • Enable cuDF/cuPy inputs in XGBClassifier (#6269)
    • Document tree method for feature weights. (#6312)
    • Add fail_on_invalid_gpu_id parameter, which will cause XGBoost to terminate upon seeing an invalid value of gpu_id (#6342)

    Breaking: the default evaluation metric for classification is changed to logloss / mlogloss (#6183)

    • The default metric used to be accuracy, and it is not statistically consistent to perform early stopping with the accuracy metric when we are really optimizing the log loss for the binary:logistic objective.
    • For statistical consistency, the default metric for classification has been changed to logloss. Users may choose to preserve the old behavior by explicitly specifying eval_metric.

    Breaking: skmaker is now removed (#5971)

    • The skmaker updater has not been documented nor tested.

    Breaking: the JSON model format no longer stores the leaf child count (#6094).

    • The leaf child count field has been deprecated and is not used anywhere in the XGBoost codebase.

    Breaking: XGBoost now requires MacOS 10.14 (Mojave) and later.

    • Homebrew has dropped support for MacOS 10.13 (High Sierra), so we are not able to install the OpenMP runtime (libomp) from Homebrew on MacOS 10.13. Please use MacOS 10.14 (Mojave) or later.

    Deprecation notices

    • The use of LabelEncoder in XGBClassifier is now deprecated and will be removed in the next minor release (#6269). The deprecation is necessary to support multiple types of inputs, such as cuDF data frames or cuPy arrays.
    • The use of certain positional arguments in the Python interface is deprecated (#6365). Users will use deprecation warnings for the use of position arguments for certain function parameters. New code should use keyword arguments as much as possible. We have not yet decided when we will fully require the use of keyword arguments.


    • On big-endian arch, swap the byte order in the binary serializer to enable loading models that were produced by a little-endian machine (#5813).
    • [jvm-packages] Fix deterministic partitioning with dataset containing Double.NaN (#5996)
    • Limit tree depth for GPU hist to 31 to prevent integer overflow (#6045)
    • [jvm-packages] Set maxBins to 256 to align with the default value in the C++ code (#6066)
    • [R] Fix CRAN check (#6077)
    • Add back support for scipy.sparse.coo_matrix (#6162)
    • Handle duplicated values in sketching. (#6178)
    • Catch all standard exceptions in C API. (#6220)
    • Fix linear GPU input (#6255)
    • Fix inplace prediction interval. (#6259)
    • [R] allow xgb.plot.importance() calls to fill a grid (#6294)
    • Lazy import dask libraries. (#6309)
    • Deterministic data partitioning for external memory (#6317)
    • Avoid resetting seed for every configuration. (#6349)
    • Fix label errors in graph visualization (#6369)
    • [jvm-packages] fix potential unit test suites aborted issue due to race condition (#6373)
    • [R] Fix warnings from R check --as-cran (#6374)
    • [R] Fix a crash that occurs with noLD R (#6378)
    • [R] Do not convert continuous labels to factors (#6380)
    • [R] remove uses of exists() (#6387)
    • Propagate parameters to the underlying Booster handle from XGBClassifier.set_param / XGBRegressor.set_param. (#6416)
    • [R] Fix R package installation via CMake (#6423)
    • Enforce row-major order in cuPy array (#6459)
    • Fix filtering callable objects in the parameters passed to the scikit-learn API. (#6466)

    Maintenance: Testing, continuous integration, build system

    • [CI] Improve JVM test in GitHub Actions (#5930)
    • Refactor plotting test so that it can run independently (#6040)
    • [CI] Cancel builds on subsequent pushes (#6011)
    • Fix Dask Pytest fixture (#6024)
    • [CI] Migrate linters to GitHub Actions (#6035)
    • [CI] Remove win2016 JVM test from GitHub Actions (#6042)
    • Fix CMake build with BUILD_STATIC_LIB option (#6090)
    • Don't link imported target in CMake (#6093)
    • Work around a compiler bug in MacOS AppleClang 11 (#6103)
    • [CI] Fix CTest by running it in a correct directory (#6104)
    • [R] Check warnings explicitly for model compatibility tests (#6114)
    • [jvm-packages] add xgboost4j-gpu/xgboost4j-spark-gpu module to facilitate release (#6136)
    • [CI] Time GPU tests. (#6141)
    • [R] remove warning in (#6152)
    • [CI] Upgrade cuDF and RMM to 0.16 nightlies; upgrade to Ubuntu 18.04 (#6157)
    • [CI] Test C API demo (#6159)
    • Option for generating device debug info. (#6168)
    • Update .gitignore (#6175, #6193, #6346)
    • Hide C++ symbols from dmlc-core (#6188)
    • [CI] Added arm64 job in Travis-CI (#6200)
    • [CI] Fix Docker build for CUDA 11 (#6202)
    • [CI] Move non-OpenMP gtest to GitHub Actions (#6210)
    • [jvm-packages] Fix up build for xgboost4j-gpu, xgboost4j-spark-gpu (#6216)
    • Add more tests for categorical data support (#6219)
    • [dask] Test for data initializaton. (#6226)
    • Bump junit from 4.11 to 4.13.1 in /jvm-packages/xgboost4j (#6230)
    • Bump junit from 4.11 to 4.13.1 in /jvm-packages/xgboost4j-gpu (#6233)
    • [CI] Reduce testing load with RMM (#6249)
    • [CI] Build a Python wheel for aarch64 platform (#6253)
    • [CI] Time the CPU tests on Jenkins. (#6257)
    • [CI] Skip Dask tests on ARM. (#6267)
    • Fix a typo in is_arm() in (#6271)
    • [CI] replace egrep with grep -E (#6287)
    • Support unity build. (#6295)
    • [CI] Mark flaky tests as XFAIL (#6299)
    • [CI] Use separate Docker cache for each CUDA version (#6305)
    • Added USE_NCCL_LIB_PATH option to enable user to set NCCL_LIBRARY during build (#6310)
    • Fix flaky data initialization test. (#6318)
    • Add a badge for GitHub Actions (#6321)
    • Optional find_package for sanitizers. (#6329)
    • Use pytest conventions consistently in Python tests (#6337)
    • Fix missing space in warning message (#6340)
    • Update custom_metric_obj.rst (#6367)
    • [CI] Run R check with --as-cran flag on GitHub Actions (#6371)
    • [CI] Remove R check from Jenkins (#6372)
    • Mark GPU external memory test as XFAIL. (#6381)
    • [CI] Add noLD R test (#6382)
    • Fix MPI build. (#6403)
    • [CI] Upgrade to MacOS Mojave image (#6406)
    • Fix flaky sparse page dmatrix test. (#6417)
    • [CI] Upgrade cuDF and RMM to 0.17 nightlies (#6434)
    • [CI] Fix CentOS 6 Docker images (#6467)
    • [CI] Vendor libgomp in the manylinux Python wheel (#6461)
    • [CI] Hot fix for libgomp vendoring (#6482)

    Maintenance: Clean up and merge the Rabit submodule (#6023, #6095, #6096, #6105, #6110, #6262, #6275, #6290)

    • The Rabit submodule is now maintained as part of the XGBoost codebase.
    • Tests for Rabit are now part of the test suites of XGBoost.
    • Rabit can now be built on the Windows platform.
    • We made various code re-formatting for the C++ code with clang-tidy.
    • Public headers of XGBoost no longer depend on Rabit headers.
    • Unused CMake targets for Rabit were removed.
    • Single-point model recovery has been dropped and removed from Rabit, simplifying the Rabit code greatly. The single-point model recovery feature has not been adequately maintained over the years.
    • We removed the parts of Rabit that were not useful for XGBoost.

    Maintenance: Refactor code for legibility and maintainability

    • Unify CPU hist sketching (#5880)
    • [R] fix uses of 1:length(x) and other small things (#5992)
    • Unify evaluation functions. (#6037)
    • Make binary bin search reusable. (#6058)
    • Unify set index data. (#6062)
    • [R] Remove stringi dependency (#6109)
    • Merge extract cuts into QuantileContainer. (#6125)
    • Reduce C++ compiler warnings (#6197, #6198, #6213, #6286, #6325)
    • Cleanup Python code. (#6223)
    • Small cleanup to evaluator. (#6400)

    Usability Improvements, Documentation

    • [jvm-packages] add example to handle missing value other than 0 (#5677)
    • Add DMatrix usage examples to the C API demo (#5854)
    • List DaskDeviceQuantileDMatrix in the doc. (#5975)
    • Update Python custom objective demo. (#5981)
    • Update the JSON model schema to document more objective functions. (#5982)
    • [Python] Fix warning when missing field is not used. (#5969)
    • Fix typo in tracker logging (#5994)
    • Move a warning about empty dataset, so that it's shown for all objectives and metrics (#5998)
    • Fix the instructions for installing the nightly build. (#6004)
    • [Doc] Add dtreeviz as a showcase example of integration with 3rd-party software (#6013)
    • [jvm-packages] [doc] Update install doc for JVM packages (#6051)
    • Fix typo in xgboost.callback.early_stop docstring (#6071)
    • Add cache suffix to the files used in the external memory demo. (#6088)
    • [Doc] Document the parameter kill_spark_context_on_worker_failure (#6097)
    • Fix link to the demo for custom objectives (#6100)
    • Update Dask doc. (#6108)
    • Validate weights are positive values. (#6115)
    • Document the updated CMake version requirement. (#6123)
    • Add demo for DaskDeviceQuantileDMatrix. (#6156)
    • Cosmetic fixes in faq.rst (#6161)
    • Fix error message. (#6176)
    • [Doc] Add list of winning solutions in data science competitions using XGBoost (#6177)
    • Fix a comment in demo to use correct reference (#6190)
    • Update the list of winning solutions using XGBoost (#6192)
    • Consistent style for build status badge (#6203)
    • [Doc] Add info on GPU compiler (#6204)
    • Update the list of winning solutions (#6222, #6254)
    • Add link to XGBoost's Twitter handle (#6244)
    • Fix minor typos in XGBClassifier methods' docstrings (#6247)
    • Add sponsors link to FUNDING.yml (#6252)
    • Group CLI demo into subdirectory. (#6258)
    • Reduce warning messages from gbtree. (#6273)
    • Create a tutorial for using the C API in a C/C++ application (#6285)
    • Update plugin instructions for CMake build (#6289)
    • [doc] make Dask distributed example copy-pastable (#6345)
    • [Python] Add option to use from the system path (#6362)
    • Fixed few grammatical mistakes in doc (#6393)
    • Fix broken link in CLI doc (#6396)
    • Improve documentation for the Dask API (#6413)
    • Revise misleading exception information: no such param of allow_non_zero_missing (#6418)
    • Fix CLI ranking demo. (#6439)
    • Fix broken links. (#6455)


    Contributors: Nan Zhu (@CodingCat), @FelixYBW, Jack Dunn (@JackDunnNZ), Jean Lescut-Muller (@JeanLescut), Boris Feld (@Lothiraldan), Nikhil Choudhary (@Nikhil1O1), Rory Mitchell (@RAMitchell), @ShvetsKS, Anthony D'Amato (@Totoketchup), @Wittty-Panda, neko (@akiyamaneko), Alexander Gugel (@alexanderGugel), @dependabot[bot], DIVYA CHAUHAN (@divya661), Daniel Steinberg (@dstein64), Akira Funahashi (@funasoul), Philip Hyunsu Cho (@hcho3), Tong He (@hetong007), Hristo Iliev (@hiliev), Honza Sterba (@honzasterba), @hzy001, Igor Moura (@igormp), @jameskrach, James Lamb (@jameslamb), Naveed Ahmed Saleem Janvekar (@janvekarnaveed), Kyle Nicholson (@kylejn27), lacrosse91 (@lacrosse91), Christian Lorentzen (@lorentzenchr), Manikya Bardhan (@manikyabard), @nabokovas, John Quitto-Graham (@nvidia-johnq), @odidev, Qi Zhang (@qzhang90), Sergio Gavilán (@sgavil), Tanuja Kirthi Doddapaneni (@tanuja3), Cuong Duong (@tcuongd), Yuan Tang (@terrytangyuan), Jiaming Yuan (@trivialfis), vcarpani (@vcarpani), Vladislav Epifanov (@vepifanov), Vitalie Spinu (@vspinu), Bobby Wang (@wbo4958), Zeno Gantner (@zenogantner), zhang_jf (@zuston)

    Reviewers: Nan Zhu (@CodingCat), John Zedlewski (@JohnZed), Rory Mitchell (@RAMitchell), @ShvetsKS, Egor Smirnov (@SmirnovEgorRu), Anthony D'Amato (@Totoketchup), @Wittty-Panda, Alexander Gugel (@alexanderGugel), Codecov Comments Bot (@codecov-commenter), Codecov (@codecov-io), DIVYA CHAUHAN (@divya661), Devin Robison (@drobison00), Geoffrey Blake (@geoffreyblake), Mark Harris (@harrism), Philip Hyunsu Cho (@hcho3), Honza Sterba (@honzasterba), Igor Moura (@igormp), @jakirkham, @jameskrach, James Lamb (@jameslamb), Janakarajan Natarajan (@janaknat), Jake Hemstad (@jrhemstad), Keith Kraus (@kkraus14), Kyle Nicholson (@kylejn27), Christian Lorentzen (@lorentzenchr), Michael Mayer (@mayer79), Nikolay Petrov (@napetrov), @odidev, PSEUDOTENSOR / Jonathan McKinney (@pseudotensor), Qi Zhang (@qzhang90), Sergio Gavilán (@sgavil), Scott Lundberg (@slundberg), Cuong Duong (@tcuongd), Yuan Tang (@terrytangyuan), Jiaming Yuan (@trivialfis), vcarpani (@vcarpani), Vladislav Epifanov (@vepifanov), Vincent Nijs (@vnijs), Vitalie Spinu (@vspinu), Bobby Wang (@wbo4958), William Hicks (@wphicks)

    Source code(tar.gz)
    Source code(zip)
  • v1.3.0rc1(Nov 23, 2020)

  • v1.2.1(Oct 14, 2020)

  • v1.2.0(Aug 23, 2020)

    XGBoost4J-Spark now supports the GPU algorithm (#5171)

    • Now XGBoost4J-Spark is able to leverage NVIDIA GPU hardware to speed up training.
    • There is on-going work for accelerating the rest of the data pipeline with NVIDIA GPUs (#5950, #5972).

    XGBoost now supports CUDA 11 (#5808)

    • It is now possible to build XGBoost with CUDA 11. Note that we do not yet distribute pre-built binaries built with CUDA 11; all current distributions use CUDA 10.0.

    Better guidance for persisting XGBoost models in an R environment (#5940, #5964)

    • Users are strongly encouraged to use and instead of saveRDS(). This is so that the persisted models can be accessed with future releases of XGBoost.
    • The previous release (1.1.0) had problems loading models that were saved with saveRDS(). This release adds a compatibility layer to restore access to the old RDS files. Note that this is meant to be a temporary measure; users are advised to stop using saveRDS() and migrate to and

    New objectives and metrics

    • The pseudo-Huber loss reg:pseudohubererror is added (#5647). The corresponding metric is mphe. Right now, the slope is hard-coded to 1.
    • The Accelerated Failure Time objective for survival analysis (survival:aft) is now accelerated on GPUs (#5714, #5716). The survival metrics aft-nloglik and interval-regression-accuracy are also accelerated on GPUs.

    Improved integration with scikit-learn

    • Added n_features_in_ attribute to the scikit-learn interface to store the number of features used (#5780). This is useful for integrating with some scikit-learn features such as StackingClassifier. See this link for more details.
    • XGBoostError now inherits ValueError, which conforms scikit-learn's exception requirement (#5696).

    Improved integration with Dask

    • The XGBoost Dask API now exposes an asynchronous interface (#5862). See the document for details.
    • Zero-copy ingestion of GPU arrays via DaskDeviceQuantileDMatrix (#5623, #5799, #5800, #5803, #5837, #5874, #5901): Previously, the Dask interface had to make 2 data copies: one for concatenating the Dask partition/block into a single block and another for internal representation. To save memory, we introduce DaskDeviceQuantileDMatrix. As long as Dask partitions are resident in the GPU memory, DaskDeviceQuantileDMatrix is able to ingest them directly without making copies. This matrix type wraps DeviceQuantileDMatrix.
    • The prediction function now returns GPU Series type if the input is from Dask-cuDF (#5710). This is to preserve the input data type.

    Robust handling of external data types (#5689, #5893)

    • As we support more and more external data types, the handling logic has proliferated all over the code base and became hard to keep track. It also became unclear how missing values and threads are handled. We refactored the Python package code to collect all data handling logic to a central location, and now we have an explicit list of of all supported data types.

    Improvements in GPU-side data matrix (DeviceQuantileDMatrix)

    • The GPU-side data matrix now implements its own quantile sketching logic, so that data don't have to be transported back to the main memory (#5700, #5747, #5760, #5846, #5870, #5898). The GK sketching algorithm is also now better documented.
      • Now we can load extremely sparse dataset like URL, although performance is still sub-optimal.
    • The GPU-side data matrix now exposes an iterative interface (#5783), so that users are able to construct a matrix from a data iterator. See the Python demo.

    New language binding: Swift (#5728)

    • Visit for more details.

    Robust model serialization with JSON (#5772, #5804, #5831, #5857, #5934)

    • We continue efforts from the 1.0.0 release to adopt JSON as the format to save and load models robustly.
    • JSON model IO is significantly faster and produces smaller model files.
    • Round-trip reproducibility is guaranteed, via the introduction of an efficient float-to-string conversion algorithm known as the Ryū algorithm. The conversion is locale-independent, producing consistent numeric representation regardless of the locale setting of the user's machine.
    • We fixed an issue in loading large JSON files to memory.
    • It is now possible to load a JSON file from a remote source such as S3.

    Performance improvements

    • CPU hist tree method optimization
      • Skip missing lookup in hist row partitioning if data is dense. (#5644)
      • Specialize training procedures for CPU hist tree method on distributed environment. (#5557)
      • Add single point histogram for CPU hist. Previously gradient histogram for CPU hist is hard coded to be 64 bit, now users can specify the parameter single_precision_histogram to use 32 bit histogram instead for faster training performance. (#5624, #5811)
    • GPU hist tree method optimization
      • Removed some unnecessary synchronizations and better memory allocation pattern. (#5707)
      • Optimize GPU Hist for wide dataset. Previously for wide dataset the atomic operation is performed on global memory, now it can run on shared memory for faster histogram building. But there's a known small regression on GeForce cards with dense data. (#5795, #5926, #5948, #5631)

    API additions

    • Support passing fmap to importance plot (#5719). Now importance plot can show actual names of features instead of default ones.
    • Support 64bit seed. (#5643)
    • A new C API XGBoosterGetNumFeature is added for getting number of features in booster (#5856).
    • Feature names and feature types are now stored in C++ core and saved in binary DMatrix (#5858).

    Breaking: The predict() method of DaskXGBClassifier now produces class predictions (#5986). Use predict_proba() to obtain probability predictions.

    • Previously, DaskXGBClassifier.predict() produced probability predictions. This is inconsistent with the behavior of other scikit-learn classifiers, where predict() returns class predictions. We make a breaking change in 1.2.0 release so that DaskXGBClassifier.predict() now correctly produces class predictions and thus behave like other scikit-learn classifiers. Furthermore, we introduce the predict_proba() method for obtaining probability predictions, again to be in line with other scikit-learn classifiers.

    Breaking: Custom evaluation metric now receives raw prediction (#5954)

    • Previously, the custom evaluation metric received a transformed prediction result when used with a classifier. Now the custom metric will receive a raw (untransformed) prediction and will need to transform the prediction itself. See demo/guide-python/ for an example.
    • This change is to make the custom metric behave consistently with the custom objective, which already receives raw prediction (#5564).

    Breaking: XGBoost4J-Spark now requires Spark 3.0 and Scala 2.12 (#5836, #5890)

    • Starting with version 3.0, Spark can manage GPU resources and allocate them among executors.
    • Spark 3.0 dropped support for Scala 2.11 and now only supports Scala 2.12. Thus, XGBoost4J-Spark also only supports Scala 2.12.

    Breaking: XGBoost Python package now requires Python 3.6 and later (#5715)

    • Python 3.6 has many useful features such as f-strings.

    Breaking: XGBoost now adopts the C++14 standard (#5664)

    • Make sure to use a sufficiently modern C++ compiler that supports C++14, such as Visual Studio 2017, GCC 5.0+, and Clang 3.4+.


    • Fix a data race in the prediction function (#5853). As a byproduct, the prediction function now uses a thread-local data store and became thread-safe.
    • Restore capability to run prediction when the test input has fewer features than the training data (#5955). This capability is necessary to support predicting with LIBSVM inputs. The previous release (1.1) had broken this capability, so we restore it in this version with better tests.
    • Fix OpenMP build with CMake for R package, to support CMake 3.13 (#5895).
    • Fix Windows 2016 build (#5902, #5918).
    • Fix edge cases in scikit-learn interface with Pandas input by disabling feature validation. (#5953)
    • [R] Enable weighted learning to rank (#5945)
    • [R] Fix early stopping with custom objective (#5923)
    • Fix NDK Build (#5886)
    • Add missing explicit template specializations for greater portability (#5921)
    • Handle empty rows in data iterators correctly (#5929). This bug affects file loader and JVM data frames.
    • Fix IsDense (#5702)
    • [jvm-packages] Fix wrong method name setAllowZeroForMissingValue (#5740)
    • Fix shape inference for Dask predict (#5989)

    Usability Improvements, Documentation

    • [Doc] Document that CUDA 10.0 is required (#5872)
    • Refactored command line interface (CLI). Now CLI is able to handle user errors and output basic document. (#5574)
    • Better error handling in Python: use raise from syntax to preserve full stacktrace (#5787).
    • The JSON model dump now has a formal schema (#5660, #5818). The benefit is to prevent dump_model() function from breaking. See this document to understand the difference between saving and dumping models.
    • Add a reference to the GPU external memory paper (#5684)
    • Document more objective parameters in the R package (#5682)
    • Document the existence of pre-built binary wheels for MacOS (#5711)
    • Remove max.depth in the R gblinear example. (#5753)
    • Added conda environment file for building docs (#5773)
    • Mention dask blog post in the doc, which introduces using Dask with GPU and some internal workings. (#5789)
    • Fix rendering of Markdown docs (#5821)
    • Document new objectives and metrics available on GPUs (#5909)
    • Better message when no GPU is found. (#5594)
    • Remove the use of silent parameter from R demos. (#5675)
    • Don't use masked array in array interface. (#5730)
    • Update affiliation of @terrytangyuan: Ant Financial -> Ant Group (#5827)
    • Move dask tutorial closer other distributed tutorials (#5613)
    • Update XGBoost + Dask overview documentation (#5961)
    • Show n_estimators in the docstring of the scikit-learn interface (#6041)
    • Fix a type in a doctring of the scikit-learn interface (#5980)

    Maintenance: testing, continuous integration, build system

    • [CI] Remove CUDA 9.0 from CI (#5674, #5745)
    • Require CUDA 10.0+ in CMake build (#5718)
    • [R] Remove dependency on gendef for Visual Studio builds (fixes #5608) (#5764). This enables building XGBoost with GPU support with R 4.x.
    • [R-package] Reduce duplication in (#5693)
    • Bump com.esotericsoftware to 4.0.2 (#5690)
    • Migrate some tests from AppVeyor to GitHub Actions to speed up the tests. (#5911, #5917, #5919, #5922, #5928)
    • Reduce cost of the Jenkins CI server (#5884, #5904, #5892). We now enforce a daily budget via an automated monitor. We also dramatically reduced the workload for the Windows platform, since the cloud VM cost is vastly greater for Windows.
    • [R] Set up automated R linter (#5944)
    • [R] replace uses of T and F with TRUE and FALSE (#5778)
    • Update Docker container 'CPU' (#5956)
    • Simplify CMake build with modern CMake techniques (#5871)
    • Use hypothesis package for testing (#5759, #5835, #5849).
    • Define _CRT_SECURE_NO_WARNINGS to remove unneeded warnings in MSVC (#5434)
    • Run all Python demos in CI, to ensure that they don't break (#5651)
    • Enhance nvtx support (#5636). Now we can use unified timer between CPU and GPU. Also CMake is able to find nvtx automatically.
    • Speed up python test. (#5752)
    • Add helper for generating batches of data. (#5756)
    • Add c-api-demo to .gitignore (#5855)
    • Add option to enable all compiler warnings in GCC/Clang (#5897)
    • Make Python model compatibility test runnable locally (#5941)
    • Add cupy to Windows CI (#5797)
    • [CI] Fix cuDF install; merge 'gpu' and 'cudf' test suite (#5814)
    • Update rabit submodule (#5680, #5876)
    • Force colored output for Ninja build. (#5959)
    • [CI] Assign larger /dev/shm to NCCL (#5966)
    • Add missing Pytest marks to AsyncIO unit test (#5968)
    • [CI] Use latest cuDF and dask-cudf (#6048)
    • Add CMake flag to log C API invocations, to aid debugging (#5925)
    • Fix a unit test on CLI, to handle RC versions (#6050)
    • [CI] Use mgpu machine to run gpu hist unit tests (#6050)
    • [CI] Build GPU-enabled JAR artifact and deploy to xgboost-maven-repo (#6050)

    Maintenance: Refactor code for legibility and maintainability

    • Remove dead code in DMatrix initialization. (#5635)
    • Catch dmlc error by ref. (#5678)
    • Refactor the gpu_hist split evaluation in preparation for batched nodes enumeration. (#5610)
    • Remove column major specialization. (#5755)
    • Remove unused imports in Python (#5776)
    • Avoid including c_api.h in header files. (#5782)
    • Remove unweighted GK quantile, which is unused. (#5816)
    • Add Python binding for rabit ops. (#5743)
    • Implement Empty method for host device vector. (#5781)
    • Remove print (#5867)
    • Enforce tree order in JSON (#5974)


    Contributors: Nan Zhu (@CodingCat), @LionOrCatThatIsTheQuestion, Dmitry Mottl (@Mottl), Rory Mitchell (@RAMitchell), @ShvetsKS, Alex Wozniakowski (@a-wozniakowski), Alexander Gugel (@alexanderGugel), @anttisaukko, @boxdot, Andy Adinets (@canonizer), Ram Rachum (@cool-RR), Elliot Hershberg (@elliothershberg), Jason E. Aten, Ph.D. (@glycerine), Philip Hyunsu Cho (@hcho3), @jameskrach, James Lamb (@jameslamb), James Bourbeau (@jrbourbeau), Peter Jung (@kongzii), Lorenz Walthert (@lorenzwalthert), Oleksandr Kuvshynov (@okuvshynov), Rong Ou (@rongou), Shaochen Shi (@shishaochen), Yuan Tang (@terrytangyuan), Jiaming Yuan (@trivialfis), Bobby Wang (@wbo4958), Zhang Zhang (@zhangzhang10)

    Reviewers: Nan Zhu (@CodingCat), @LionOrCatThatIsTheQuestion, Hao Yang (@QuantHao), Rory Mitchell (@RAMitchell), @ShvetsKS, Egor Smirnov (@SmirnovEgorRu), Alex Wozniakowski (@a-wozniakowski), Amit Kumar (@aktech), Avinash Barnwal (@avinashbarnwal), @boxdot, Andy Adinets (@canonizer), Chandra Shekhar Reddy (@chandrureddy), Ram Rachum (@cool-RR), Cristiano Goncalves (@cristianogoncalves), Elliot Hershberg (@elliothershberg), Jason E. Aten, Ph.D. (@glycerine), Philip Hyunsu Cho (@hcho3), Tong He (@hetong007), James Lamb (@jameslamb), James Bourbeau (@jrbourbeau), Lee Drake (@leedrake5), DougM (@mengdong), Oleksandr Kuvshynov (@okuvshynov), RongOu (@rongou), Shaochen Shi (@shishaochen), Xu Xiao (@sperlingxx), Yuan Tang (@terrytangyuan), Theodore Vasiloudis (@thvasilo), Jiaming Yuan (@trivialfis), Bobby Wang (@wbo4958), Zhang Zhang (@zhangzhang10)

    Source code(tar.gz)
    Source code(zip)
  • v1.2.0rc2(Aug 12, 2020)

  • v1.2.0rc1(Aug 2, 2020)

  • v1.1.1(Jun 7, 2020)

    This patch release applies the following patches to 1.1.0 release:

    • CPU performance improvement in the PyPI wheels (#5720)
    • Fix loading old model. (#5724)
    • Install pkg-config file (#5744)
    Source code(tar.gz)
    Source code(zip)
  • v1.1.0(May 17, 2020)

    Better performance on multi-core CPUs (#5244, #5334, #5522)

    • Poor performance scaling of the hist algorithm for multi-core CPUs has been under investigation (#3810). #5244 concludes the ongoing effort to improve performance scaling on multi-CPUs, in particular Intel CPUs. Roadmap: #5104
    • #5334 makes steps toward reducing memory consumption for the hist tree method on CPU.
    • #5522 optimizes random number generation for data sampling.

    Deterministic GPU algorithm for regression and classification (#5361)

    • GPU algorithm for regression and classification tasks is now deterministic.
    • Roadmap: #5023. Currently only single-GPU training is deterministic. Distributed training with multiple GPUs is not yet deterministic.

    Improve external memory support on GPUs (#5093, #5365)

    • Starting from 1.0.0 release, we added support for external memory on GPUs to enable training with larger datasets. Gradient-based sampling (#5093) speeds up the external memory algorithm by intelligently sampling a subset of the training data to copy into the GPU memory. Learn more about out-of-core GPU gradient boosting.
    • GPU-side data sketching now works with data from external memory (#5365).

    Parameter validation: detection of unused or incorrect parameters (#5477, #5569, #5508)

    • Mis-spelled training parameter is a common user mistake. In previous versions of XGBoost, mis-spelled parameters were silently ignored. Starting with 1.0.0 release, XGBoost will produce a warning message if there is any unused training parameters. The 1.1.0 release makes parameter validation available to the scikit-learn interface (#5477) and the R binding (#5569).

    Thread-safe, in-place prediction method (#5389, #5512)

    • Previously, the prediction method was not thread-safe (#5339). This release adds a new API function inplace_predict() that is thread-safe. It is now possible to serve concurrent requests for prediction using a shared model object.
    • It is now possible to compute prediction in-place for selected data formats (numpy.ndarray / scipy.sparse.csr_matrix / cupy.ndarray / cudf.DataFrame / pd.DataFrame) without creating a DMatrix object.

    Addition of Accelerated Failure Time objective for survival analysis (#4763, #5473, #5486, #5552, #5553)

    • Survival analysis (regression) models the time it takes for an event of interest to occur. The target label is potentially censored, i.e. the label is a range rather than a single number. We added a new objective survival:aft to support survival analysis. Also added is the new API to specify the ranged labels. Check out the tutorial and the demos.
    • GPU support is work in progress (#5714).

    Improved installation experience on Mac OSX (#5597, #5602, #5606, #5701)

    • It only takes two commands to install the XGBoost Python package: brew install libomp followed by pip install xgboost. The installed XGBoost will use all CPU cores. Even better, starting with this release, we distribute pre-compiled binary wheels targeting Mac OSX. Now the install command pip install xgboost finishes instantly, as it no longer compiles the C++ source of XGBoost. The last three Mac versions (High Sierra, Mojave, Catalina) are supported.
    • R package: the 1.1.0 release fixes the error Initializing libomp.dylib, but found libomp.dylib already initialized (#5701)

    Ranking metrics are now accelerated on GPUs (#5380, #5387, #5398)

    GPU-side data matrix to ingest data directly from other GPU libraries (#5420, #5465)

    • Previously, data on GPU memory had to be copied back to the main memory before it could be used by XGBoost. Starting with 1.1.0 release, XGBoost provides a dedicated interface (DeviceQuantileDMatrix) so that it can ingest data from GPU memory directly. The result is that XGBoost interoperates better with GPU-accelerated data science libraries, such as cuDF, cuPy, and PyTorch.
    • Set device in device dmatrix. (#5596)

    Robust model serialization with JSON (#5123, #5217)

    • We continue efforts from the 1.0.0 release to adopt JSON as the format to save and load models robustly. Refer to the release note for 1.0.0 to learn more.
    • It is now possible to store internal configuration of the trained model (Booster) object in R as a JSON string (#5123, #5217).

    Improved integration with Dask

    • Pass through verbose parameter for dask fit (#5413)
    • Use DMLC_TASK_ID. (#5415)
    • Order the prediction result. (#5416)
    • Honor nthreads from dask worker. (#5414)
    • Enable grid searching with scikit-learn. (#5417)
    • Check non-equal when setting threads. (#5421)
    • Accept other inputs for prediction. (#5428)
    • Fix missing value for scikit-learn interface. (#5435)

    XGBoost4J-Spark: Check number of columns in the data iterator (#5202, #5303)

    • Before, the native layer in XGBoost did not know the number of columns (features) ahead of time and had to guess the number of columns by counting the feature index when ingesting data. This method has a failure more in distributed setting: if the training data is highly sparse, some features may be completely missing in one or more worker partitions. Thus, one or more workers may deduce an incorrect data shape, leading to crashes or silently wrong models.
    • Enforce correct data shape by passing the number of columns explicitly from the JVM layer into the native layer.

    Major refactoring of the DMatrix class

    • Continued from 1.0.0 release.
    • Remove update prediction cache from predictors. (#5312)
    • Predict on Ellpack. (#5327)
    • Partial rewrite EllpackPage (#5352)
    • Use ellpack for prediction only when sparsepage doesn't exist. (#5504)
    • RFC: #4354, Roadmap: #5143

    Breaking: XGBoost Python package now requires Pip 19.0 and higher (#5589)

    • Your Linux machine may have an old version of Pip and may attempt to install a source package, leading to long installation time. This is because we are now using manylinux2010 tag in the binary wheel release. Ensure you have Pip 19.0 or newer by running python3 -m pip -V to check the version. Upgrade Pip with command
    python3 -m pip install --upgrade pip

    Upgrading to latest pip allows us to depend on newer versions of system libraries. TensorFlow also requires Pip 19.0+.

    Breaking: GPU algorithm now requires CUDA 10.0 and higher (#5649)

    • CUDA 10.0 is necessary to make the GPU algorithm deterministic (#5361).

    Breaking: silent parameter is now removed (#5476)

    • Please use verbosity instead.

    Breaking: Set output_margin to True for custom objectives (#5564)

    • Now both R and Python interface custom objectives get un-transformed (raw) prediction outputs.

    Breaking: Makefile is now removed. We use CMake exclusively to build XGBoost (#5513)

    • Exception: the R package uses Autotools, as the CRAN ecosystem did not yet adopt CMake widely.

    Breaking: distcol updater is now removed (#5507)

    • The distcol updater has been long broken, and currently we lack resources to implement a working implementation from scratch.

    Deprecation notices

    • Python 3.5. This release is the last release to support Python 3.5. The following release (1.2.0) will require Python 3.6.
    • Scala 2.11. Currently XGBoost4J supports Scala 2.11. However, if a future release of XGBoost adopts Spark 3, it will not support Scala 2.11, as Spark 3 requires Scala 2.12+. We do not yet know which XGBoost release will adopt Spark 3.

    Known limitations

    • (Python package) When early stopping is activated with early_stopping_rounds at training time, the prediction method (xgb.predict()) behaves in a surprising way. If XGBoost runs for M rounds and chooses iteration N (N < M) as the best iteration, then the prediction method will use M trees by default. To use the best iteration (N trees), users will need to manually take the best iteration field bst.best_iteration and pass it as the ntree_limit argument to xgb.predict(). See #5209 and #4052 for additional context.
    • GPU ranking objective is currently not deterministic (#5561).
    • When training parameter reg_lambda is set to zero, some leaf nodes may be assigned a NaN value. (See discussion.) For now, please set reg_lambda to a nonzero value.

    Community and Governance

    • The XGBoost Project Management Committee (PMC) is pleased to announce a new committer: Egor Smirnov (@SmirnovEgorRu). He has led a major initiative to improve the performance of XGBoost on multi-core CPUs.


    • Improved compatibility with scikit-learn (#5255, #5505, #5538)
    • Remove f-string, since it's not supported by Python 3.5 (#5330). Note that Python 3.5 support is deprecated and schedule to be dropped in the upcoming release (1.2.0).
    • Fix the pruner so that it doesn't prune the same branch twice (#5335)
    • Enforce only major version in JSON model schema (#5336). Any major revision of the model schema would bump up the major version.
    • Fix a small typo in that broke multiple eval metrics (#5341)
    • Restore loading model from a memory buffer (#5360)
    • Define lazy isinstance for Python compat (#5364)
    • [R] fixed uses of class() (#5426)
    • Force compressed buffer to be 4 bytes aligned, to keep cuda-memcheck happy (#5441)
    • Remove warning for calling host function (std::max) on a GPU device (#5453)
    • Fix uninitialized value bug in xgboost callback (#5463)
    • Fix model dump in CLI (#5485)
    • Fix out-of-bound array access in WQSummary::SetPrune() (#5493)
    • Ensure that configured dmlc/build_config.h is picked up by Rabit and XGBoost, to fix build on Alpine (#5514)
    • Fix a misspelled method, made in a git merge (#5509)
    • Fix a bug in binary model serialization (#5532)
    • Fix CLI model IO (#5535)
    • Don't use uint for threads (#5542)
    • Fix R interaction constraints to handle more than 100000 features (#5543)
    • [jvm-packages] XGBoost Spark should deal with NaN when parsing evaluation output (#5546)
    • GPU-side data sketching is now aware of query groups in learning-to-rank data (#5551)
    • Fix DMatrix slicing for newly added fields (#5552)
    • Fix configuration status with loading binary model (#5562)
    • Fix build when OpenMP is disabled (#5566)
    • R compatibility patches (#5577, #5600)
    • gpu_hist performance fixes (#5558)
    • Don't set seed on CLI interface (#5563)
    • [R] When serializing model, preserve model attributes related to early stopping (#5573)
    • Avoid rabit calls in learner configuration (#5581)
    • Hide C++ symbols in when building Python wheel (#5590). This fixes apache/incubator-tvm#4953.
    • Fix compilation on Mac OSX High Sierra (10.13) (#5597)
    • Fix build on big endian CPUs (#5617)
    • Resolve crash due to use of vector<bool>::iterator (#5642)
    • Validation JSON model dump using JSON schema (#5660)

    Performance improvements

    • Wide dataset quantile performance improvement (#5306)
    • Reduce memory usage of GPU-side data sketching (#5407)
    • Reduce span check overhead (#5464)
    • Serialise booster after training to free up GPU memory (#5484)
    • Use the maximum amount of GPU shared memory available to speed up the histogram kernel (#5491)
    • Use non-synchronising scan in Thrust (#5560)
    • Use cudaDeviceGetAttribute() instead of cudaGetDeviceProperties() for speed (#5570)

    API changes

    • Support importing data from a Pandas SparseArray (#5431)
    • HostDeviceVector (vector shared between CPU and GPU memory) now exposes HostSpan interface, to enable access on the CPU side with bound check (#5459)
    • Accept other gradient types for SplitEntry (#5467)

    Usability Improvements, Documentation

    • Add JVM_CHECK_CALL to prevent C++ exceptions from leaking into the JVM layer (#5199)
    • Updated Windows build docs (#5283)
    • Update affiliation of @hcho3 (#5292)
    • Display Sponsor button, link to OpenCollective (#5325)
    • Update docs for GPU external memory (#5332)
    • Add link to GPU documentation (#5437)
    • Small updates to GPU documentation (#5483)
    • Edits on tutorial for XGBoost job on Kubernetes (#5487)
    • Add reference to GPU external memory (#5490)
    • Fix typos (#5346, #5371, #5384, #5399, #5482, #5515)
    • Update Python doc (#5517)
    • Add Neptune and Optuna to list of examples (#5528)
    • Raise error if the number of data weights doesn't match the number of data sets (#5540)
    • Add a note about GPU ranking (#5572)
    • Clarify meaning of training parameter in the C API function XGBoosterPredict() (#5604)
    • Better error handling for situations where existing trees cannot be modified (#5406, #5418). This feature is enabled when process_type is set to update.

    Maintenance: testing, continuous integration, build system

    • Add C++ test coverage for data sketching (#5251)
    • Ignore gdb_history (#5257)
    • Rewrite (#5271, #5280)
    • Use scikit-learn in extra dependencies (#5310)
    • Add CMake option to build static library (#5397)
    • [R] changed FindLibR to take advantage of CMake cache (#5427)
    • [R] fixed inconsistency in R -e calls in FindLibR.cmake (#5438)
    • Refactor tests with data generator (#5439)
    • Resolve failing Travis CI (#5445)
    • Update dmlc-core. (#5466)
    • [CI] Use clang-tidy 10 (#5469)
    • De-duplicate code for checking maximum number of nodes (#5497)
    • [CI] Use Ubuntu 18.04 LTS in JVM CI, because 19.04 is EOL (#5537)
    • [jvm-packages] [CI] Create a Maven repository to host SNAPSHOT JARs (#5533)
    • [jvm-packages] [CI] Publish XGBoost4J JARs with Scala 2.11 and 2.12 (#5539)
    • [CI] Use Vault repository to re-gain access to devtoolset-4 (#5589)

    Maintenance: Refactor code for legibility and maintainability

    • Move prediction cache to Learner (#5220, #5302)
    • Remove SimpleCSRSource (#5315)
    • Refactor SparsePageSource, delete cache files after use (#5321)
    • Remove unnecessary DMatrix methods (#5324)
    • Split up LearnerImpl (#5350)
    • Move segment sorter to common (#5378)
    • Move thread local entry into Learner (#5396)
    • Split up test helpers header (#5455)
    • Requires setting leaf stat when expanding tree (#5501)
    • Purge device_helpers.cuh (#5534)
    • Use thrust functions instead of custom functions (#5544)


    Contributors: Nan Zhu (@CodingCat), Rory Mitchell (@RAMitchell), @ShvetsKS, Egor Smirnov (@SmirnovEgorRu), Andrew Kane (@ankane), Avinash Barnwal (@avinashbarnwal), Bart Broere (@bartbroere), Andy Adinets (@canonizer), Chen Qin (@chenqin), Daiki Katsuragawa (@daikikatsuragawa), David Díaz Vico (@daviddiazvico), Darius Kharazi (@dkharazi), Darby Payne (@dpayne), Jason E. Aten, Ph.D. (@glycerine), Philip Hyunsu Cho (@hcho3), James Lamb (@jameslamb), Jan Borchmann (@jborchma), Kamil A. Kaczmarek (@kamil-kaczmarek), Melissa Kohl (@mjkohl32), Nicolas Scozzaro (@nscozzaro), Paul Kaefer (@paulkaefer), Rong Ou (@rongou), Samrat Pandiri (@samratp), Sriram Chandramouli (@sriramch), Yuan Tang (@terrytangyuan), Jiaming Yuan (@trivialfis), Liang-Chi Hsieh (@viirya), Bobby Wang (@wbo4958), Zhang Zhang (@zhangzhang10)

    Reviewers: Nan Zhu (@CodingCat), @LeZhengThu, Rory Mitchell (@RAMitchell), @ShvetsKS, Egor Smirnov (@SmirnovEgorRu), Steve Bronder (@SteveBronder), Nikita Titov (@StrikerRUS), Andrew Kane (@ankane), Avinash Barnwal (@avinashbarnwal), @brydag, Andy Adinets (@canonizer), Chandra Shekhar Reddy (@chandrureddy), Chen Qin (@chenqin), Codecov (@codecov-io), David Díaz Vico (@daviddiazvico), Darby Payne (@dpayne), Jason E. Aten, Ph.D. (@glycerine), Philip Hyunsu Cho (@hcho3), James Lamb (@jameslamb), @johnny-cat, Mu Li (@mli), Mate Soos (@msoos), @rnyak, Rong Ou (@rongou), Sriram Chandramouli (@sriramch), Toby Dylan Hocking (@tdhock), Yuan Tang (@terrytangyuan), Oleksandr Pryimak (@trams), Jiaming Yuan (@trivialfis), Liang-Chi Hsieh (@viirya), Bobby Wang (@wbo4958)

    Source code(tar.gz)
    Source code(zip)
  • v1.1.0rc2(May 4, 2020)

  • v1.1.0rc1(Apr 24, 2020)

  • v1.0.2(Mar 4, 2020)

    This patch release applies the following patches to 1.0.0 release:

    • Fix a small typo in that broke multiple eval metrics (#5341)
    • Restore loading model from buffer. (#5360)
    • Use type name for data type check. (#5364)
    Source code(tar.gz)
    Source code(zip)
  • v1.0.1(Feb 21, 2020)

    This release is identical to the 1.0.0 release, except that it fixes a small bug that rendered 1.0.0 incompatible with Python 3.5. See #5328.

    Source code(tar.gz)
    Source code(zip)
  • v1.0.0(Feb 20, 2020)

    v1.0.0 (2020.02.19)

    This release marks a major milestone for the XGBoost project.

    Apache-style governance, contribution policy, and semantic versioning (#4646, #4659)

    • Starting with 1.0.0 release, the XGBoost Project is adopting Apache-style governance. The full community guideline is available in the doc website. Note that we now have Project Management Committee (PMC) who would steward the project on the long-term basis. The PMC is also entrusted to run and fund the project's continuous integration (CI) infrastructure (
    • We also adopt the semantic versioning. See our release versioning policy.

    Better performance scaling for multi-core CPUs (#4502, #4529, #4716, #4851, #5008, #5107, #5138, #5156)

    • Poor performance scaling of the hist algorithm for multi-core CPUs has been under investigation (#3810). Previous effort #4529 was replaced with a series of pull requests (#5107, #5138, #5156) aimed at achieving the same performance benefits while keeping the C++ codebase legible. The latest performance benchmark results show up to 5x speedup on Intel CPUs with many cores. Note: #5244, which concludes the effort, will become part of the upcoming release 1.1.0.

    Improved installation experience on Mac OSX (#4672, #5074, #5080, #5146, #5240)

    • It used to be quite complicated to install XGBoost on Mac OSX. XGBoost uses OpenMP to distribute work among multiple CPU cores, and Mac's default C++ compiler (Apple Clang) does not come with OpenMP. Existing work-around (using another C++ compiler) was complex and prone to fail with cryptic diagnosis (#4933, #4949, #4969).
    • Now it only takes two commands to install XGBoost: brew install libomp followed by pip install xgboost. The installed XGBoost will use all CPU cores.
    • Even better, XGBoost is now available from Homebrew: brew install xgboost. See Homebrew/homebrew-core#50467.
    • Previously, if you installed the XGBoost R package using the command install.packages('xgboost'), it could only use a single CPU core and you would experience slow training performance. With 1.0.0 release, the R package will use all CPU cores out of box.

    Distributed XGBoost now available on Kubernetes (#4621, #4939)

    Ruby binding for XGBoost (#4856)

    New Native Dask interface for multi-GPU and multi-node scaling (#4473, #4507, #4617, #4819, #4907, #4914, #4941, #4942, #4951, #4973, #5048, #5077, #5144, #5270)

    • XGBoost now integrates seamlessly with Dask, a lightweight distributed framework for data processing. Together with the first-class support for cuDF data frames (see below), it is now easier than ever to create end-to-end data pipeline running on one or more NVIDIA GPUs.
    • Multi-GPU training with Dask is now up to 20% faster than the previous release (#4914, #4951).

    First-class support for cuDF data frames and cuPy arrays (#4737, #4745, #4794, #4850, #4891, #4902, #4918, #4927, #4928, #5053, #5189, #5194, #5206, #5219, #5225)

    • cuDF is a data frame library for loading and processing tabular data on NVIDIA GPUs. It provides a Pandas-like API.
    • cuPy implements a NumPy-compatible multi-dimensional array on NVIDIA GPUs.
    • Now users can keep the data on the GPU memory throughout the end-to-end data pipeline, obviating the need for copying data between the main memory and GPU memory.
    • XGBoost can accept any data structure that exposes __array_interface__ signature, opening way to support other columar formats that are compatible with Apache Arrow.

    Feature interaction constraint is now available with approx and gpu_hist algorithms (#4534, #4587, #4596, #5034).

    Learning to rank is now GPU accelerated (#4873, #5004, #5129)

    Enable gamma parameter for GPU training (#4874, #4953)

    • The gamma parameter specifies the minimum loss reduction required to add a new split in a tree. A larger value for gamma has the effect of pre-pruning the tree, by making harder to add splits.

    External memory for GPU training (#4486, #4526, #4747, #4833, #4879, #5014)

    • It is now possible to use NVIDIA GPUs even when the size of training data exceeds the available GPU memory. Note that the external memory support for GPU is still experimental. #5093 will further improve performance and will become part of the upcoming release 1.1.0.
    • RFC for enabling external memory with GPU algorithms: #4357

    Improve Scikit-Learn interface (#4558, #4842, #4929, #5049, #5151, #5130, #5227)

    • Many users of XGBoost enjoy the convenience and breadth of Scikit-Learn ecosystem. In this release, we revise the Scikit-Learn API of XGBoost (XGBRegressor, XGBClassifier, and XGBRanker) to achieve feature parity with the traditional XGBoost interface (xgboost.train()).
    • Insert check to validate data shapes.
    • Produce an error message if eval_set is not a tuple. An error message is better than silently crashing.
    • Allow using numpy.RandomState object.
    • Add n_jobs as an alias of nthread.
    • Roadmap: #5152

    XGBoost4J-Spark: Redesigning checkpointing mechanism

    • RFC is available at #4786
    • Clean up checkpoint file after a successful training job (#4754): The current implementation in XGBoost4J-Spark does not clean up the checkpoint file after a successful training job. If the user runs another job with the same checkpointing directory, she will get a wrong model because the second job will re-use the checkpoint file left over from the first job. To prevent this scenario, we propose to always clean up the checkpoint file after every successful training job.
    • Avoid Multiple Jobs for Checkpointing (#5082): The current method for checkpoint is to collect the booster produced at the last iteration of each checkpoint internal to Driver and persist it in HDFS. The major issue with this approach is that it needs to re-perform the data preparation for training if the user did not choose to cache the training dataset. To avoid re-performing data prep, we build external-memory checkpointing in the XGBoost4J layer as well.
    • Enable deterministic repartitioning when checkpoint is enabled (#4807): Distributed algorithm for gradient boosting assumes a fixed partition of the training data between multiple iterations. In previous versions, there was no guarantee that data partition would stay the same, especially when a worker goes down and some data had to recovered from previous checkpoint. In this release, we make data partition deterministic by using the data hash value of each data row in computing the partition.

    XGBoost4J-Spark: handle errors thrown by the native code (#4560)

    • All core logic of XGBoost is written in C++, so XGBoost4J-Spark internally uses the C++ code via Java Native Interface (JNI). #4560 adds a proper error handling for any errors or exceptions arising from the C++ code, so that the XGBoost Spark application can be torn down in an orderly fashion.

    XGBoost4J-Spark: Refine method to count the number of alive cores (#4858)

    • The SparkParallelismTracker class ensures that sufficient number of executor cores are alive. To that end, it is important to query the number of alive cores reliably.

    XGBoost4J: Add BigDenseMatrix to store more than Integer.MAX_VALUE elements (#4383)

    Robust model serialization with JSON (#4632, #4708, #4739, #4868, #4936, #4945, #4974, #5086, #5087, #5089, #5091, #5094, #5110, #5111, #5112, #5120, #5137, #5218, #5222, #5236, #5245, #5248, #5281)

    • In this release, we introduce an experimental support of using JSON for serializing (saving/loading) XGBoost models and related hyperparameters for training. We would like to eventually replace the old binary format with JSON, since it is an open format and parsers are available in many programming languages and platforms. See the documentation for model I/O using JSON. #3980 explains why JSON was chosen over other alternatives.

    • To maximize interoperability and compatibility of the serialized models, we now split serialization into two parts (#4855):

      1. Model, e.g. decision trees and strictly related metadata like num_features.
      2. Internal configuration, consisting of training parameters and other configurable parameters. For example, max_delta_step, tree_method, objective, predictor, gpu_id.

      Previously, users often ran into issues where the model file produced by one machine could not load or run on another machine. For example, models trained using a machine with an NVIDIA GPU could not run on another machine without a GPU (#5291, #5234). The reason is that the old binary format saved some internal configuration that were not universally applicable to all machines, e.g. predictor='gpu_predictor'.

      Now, model saving function (Booster.save_model() in Python) will save only the model, without internal configuration. This will guarantee that your model file would be used anywhere. Internal configuration will be serialized in limited circumstances such as:

      • Multiple nodes in a distributed system exchange model details over the network.
      • Model checkpointing, to recover from possible crashes.

      This work proved to be useful for parameter validation as well (see below).

    • Starting with 1.0.0 release, we will use semantic versioning to indicate whether the model produced by one version of XGBoost would be compatible with another version of XGBoost. Any change in the major version indicates a breaking change in the serialization format.

    • We now provide a robust method to save and load scikit-learn related attributes (#5245). Previously, we used Python pickle to save Python attributes related to XGBClassifier, XGBRegressor, and XGBRanker objects. The attributes are necessary to properly interact with scikit-learn. See #4639 for more details. The use of pickling hampered interoperability, as a pickle from one machine may not necessarily work on another machine. Starting with this release, we use an alternative method to serialize the scikit-learn related attributes. The use of Python pickle is now discouraged (#5236, #5281).

    Parameter validation: detection of unused or incorrect parameters (#4553, #4577, #4738, #4801, #4961, #5101, #5157, #5167, #5256)

    • Mis-spelled training parameter is a common user mistake. In previous versions of XGBoost, mis-spelled parameters were silently ignored. Starting with 1.0.0 release, XGBoost will produce a warning message if there is any unused training parameters. Currently, parameter validation is available to R users and Python XGBoost API users. We are working to extend its support to scikit-learn users.
    • Configuration steps now have well-defined semantics (#4542, #4738), so we know exactly where and how the internal configurable parameters are changed.
    • The user can now use save_config() function to inspect all (used) training parameters. This is helpful for debugging model performance.

    Allow individual workers to recover from faults (#4808, #4966)

    • Status quo: if a worker fails, all workers are shut down and restarted, and learning resumes from the last checkpoint. This involves requesting resources from the scheduler (e.g. Spark) and shuffling all the data again from scratch. Both of these operations can be quite costly and block training for extended periods of time, especially if the training data is big and the number of worker nodes is in the hundreds.
    • The proposed solution is to recover the single node that failed, instead of shutting down all workers. The rest of the clusters wait until the single failed worker is bootstrapped and catches up with the rest.
    • See roadmap at #4753. Note that this is work in progress. In particular, the feature is not yet available from XGBoost4J-Spark.

    Accurate prediction for DART models

    • Use DART tree weights when computing SHAPs (#5050)
    • Don't drop trees during DART prediction by default (#5115)
    • Fix DART prediction in R (#5204)

    Make external memory more robust

    • Fix issues with training with external memory on cpu (#4487)
    • Fix crash with approx tree method on cpu (#4510)
    • Fix external memory race in exact (#4980). Note: dmlc::ThreadedIter is not actually thread-safe. We would like to re-design it in the long term.

    Major refactoring of the DMatrix class (#4686, #4744, #4748, #5044, #5092, #5108, #5188, #5198)

    • Goal 1: improve performance and reduce memory consumption. Right now, if the user trains a model with a NumPy array as training data, the array gets copies 2-3 times before training begins. We'd like to reduce duplication of the data matrix.
    • Goal 2: Expose a common interface to external data, unify the way DMatrix objects are constructed and simplify the process of adding new external data sources. This work is essential for ingesting cuPy arrays.
    • Goal 3: Handle missing values consistently.
    • RFC: #4354, Roadmap: #5143
    • This work is also relevant to external memory support on GPUs.

    Breaking: XGBoost Python package now requires Python 3.5 or newer (#5021, #5274)

    • Python 3.4 has reached its end-of-life on March 16, 2019, so we now require Python 3.5 or newer.

    Breaking: GPU algorithm now requires CUDA 9.0 and higher (#4527, #4580)

    Breaking: n_gpus parameter removed; multi-GPU training now requires a distributed framework (#4579, #4749, #4773, #4810, #4867, #4908)

    • #4531 proposed removing support for single-process multi-GPU training. Contributors would focus on multi-GPU support through distributed frameworks such as Dask and Spark, where the framework would be expected to assign a worker process for each GPU independently. By delegating GPU management and data movement to the distributed framework, we can greatly simplify the core XGBoost codebase, make multi-GPU training more robust, and reduce burden for future development.

    Breaking: Some deprecated features have been removed

    • gpu_exact training method (#4527, #4742, #4777). Use gpu_hist instead.
    • learning_rates parameter in Python (#5155). Use the callback API instead.
    • num_roots (#5059, #5165), since the current training code always uses a single root node.
    • GPU-specific objectives (#4690), such as gpu:reg:linear. Use objectives without gpu: prefix; GPU will be used automatically if your machine has one.

    Breaking: the C API function XGBoosterPredict() now asks for an extra parameter training.

    Breaking: We now use CMake exclusively to build XGBoost. Makefile is being sunset.

    • Exception: the R package uses Autotools, as the CRAN ecosystem did not yet adopt CMake widely.

    Performance improvements

    • Smarter choice of histogram construction for distributed gpu_hist (#4519)
    • Optimizations for quantization on device (#4572)
    • Introduce caching memory allocator to avoid latency associated with GPU memory allocation (#4554, #4615)
    • Optimize the initialization stage of the CPU hist algorithm for sparse datasets (#4625)
    • Prevent unnecessary data copies from GPU memory to the host (#4795)
    • Improve operation efficiency for single prediction (#5016)
    • Group builder modified for incremental building, to speed up building large DMatrix (#5098)


    • Eliminate FutureWarning: Series.base is deprecated (#4337)
    • Ensure pandas DataFrame column names are treated as strings in type error message (#4481)
    • [jvm-packages] Add back reg:linear for scala, as it is only deprecated and not meant to be removed yet (#4490)
    • Fix library loading for Cygwin users (#4499)
    • Fix prediction from loaded pickle (#4516)
    • Enforce exclusion between pred_interactions=True and pred_interactions=True (#4522)
    • Do not return dangling reference to local std::string (#4543)
    • Set the appropriate device before freeing device memory (#4566)
    • Mark SparsePageDmatrix destructor default. (#4568)
    • Choose the appropriate tree method only when the tree method is 'auto' (#4571)
    • Fix (#4593)
    • [jvm-packages] Fix silly bug in feature scoring (#4604)
    • Fix GPU predictor when the test data matrix has different number of features than the training data matrix used to train the model (#4613)
    • Fix external memory for get column batches. (#4622)
    • [R] Use built-in label when xgb.DMatrix is given to (#4631)
    • Fix early stopping in the Python package (#4638)
    • Fix AUC error in distributed mode caused by imbalanced dataset (#4645, #4798)
    • [jvm-packages] Expose setMissing method in XGBoostClassificationModel / XGBoostRegressionModel (#4643)
    • Remove initializing stringstream reference. (#4788)
    • [R] xgb.get.handle now checks all class listed of object (#4800)
    • Do not use gpu_predictor unless data comes from GPU (#4836)
    • Fix data loading (#4862)
    • Workaround isnan across different environments. (#4883)
    • [jvm-packages] Handle Long-type parameter (#4885)
    • Don't set_params at the end of set_state (#4947). Ensure that the model does not change after pickling and unpickling multiple times.
    • C++ exceptions should not crash OpenMP loops (#4960)
    • Fix usegpu flag in DART. (#4984)
    • Run training with empty DMatrix (#4990, #5159)
    • Ensure that no two processes can use the same GPU (#4990)
    • Fix repeated split and 0 cover nodes (#5010)
    • Reset histogram hit counter between multiple data batches (#5035)
    • Fix feature_name crated from int64index dataframe. (#5081)
    • Don't use 0 for "fresh leaf" (#5084)
    • Throw error when user attempts to use multi-GPU training and XGBoost has not been compiled with NCCL (#5170)
    • Fix metric name loading (#5122)
    • Quick fix for memory leak in CPU hist algorithm (#5153)
    • Fix wrapping GPU ID and prevent data copying (#5160)
    • Fix signature of Span constructor (#5166)
    • Lazy initialization of device vector, so that XGBoost compiled with CUDA can run on a machine without any GPU (#5173)
    • Model loading should not change system locale (#5314)
    • Distributed training jobs would sometimes hang; revert Rabit to fix this regression (dmlc/rabit#132, #5237)

    API changes

    • Add support for cross-validation using query ID (#4474)
    • Enable feature importance property for DART model (#4525)
    • Add rmsle metric and reg:squaredlogerror objective (#4541)
    • All objective and evaluation metrics are now exposed to JVM packages (#4560)
    • dump_model() and get_dump() now support exporting in GraphViz language (#4602)
    • Support metrics ndcg- and map- (#4635)
    • [jvm-packages] Allow chaining prediction (transform) in XGBoost4J-Spark (#4667)
    • [jvm-packages] Add option to bypass missing value check in the Spark layer (#4805). Only use this option if you know what you are doing.
    • [jvm-packages] Add public group getter (#4838)
    • XGDMatrixSetGroup C API is now deprecated (#4864). Use XGDMatrixSetUIntInfo instead.
    • [R] Added new train_folds parameter to (#5114)
    • Ingest meta information from Pandas DataFrame, such as data weights (#5216)

    Maintenance: Refactor code for legibility and maintainability

    • De-duplicate GPU parameters (#4454)
    • Simplify INI-style config reader using C++11 STL (#4478, #4521)
    • Refactor histogram building code for gpu_hist (#4528)
    • Overload device memory allocator, to enable instrumentation for compiling memory usage statistics (#4532)
    • Refactor out row partitioning logic from gpu_hist (#4554)
    • Remove an unused variable (#4588)
    • Implement tree model dump with code generator, to de-duplicate code for generating dumps in 3 different formats (#4602)
    • Remove RowSet class which is no longer being used (#4697)
    • Remove some unused functions as reported by cppcheck (#4743)
    • Mimic CUDA assert output in Span check (#4762)
    • [jvm-packages] Refactor XGBoost.scala to put all params processing in one place (#4815)
    • Add some comments for GPU row partitioner (#4832)
    • Span: use size_t' for index_type, addfront' and `back'. (#4935)
    • Remove dead code in exact algorithm (#5034, #5105)
    • Unify integer types used for row and column indices (#5034)
    • Extract feature interaction constraint from SplitEvaluator class. (#5034)
    • [Breaking] De-duplicate paramters and docstrings in the constructors of Scikit-Learn models (#5130)
    • Remove benchmark code from GPU tests (#5141)
    • Clean up Python 2 compatibility code. (#5161)
    • Extensible binary serialization format for DMatrix::MetaInfo (#5187). This will be useful for implementing censored labels for survival analysis applications.
    • Cleanup clang-tidy warnings. (#5247)

    Maintenance: testing, continuous integration, build system

    • Use yaml.safe_load instead of yaml.load. (#4537)
    • Ensure GCC is at least 5.x (#4538)
    • Remove all mention of reg:linear from tests (#4544)
    • [jvm-packages] Upgrade to Scala 2.12 (#4574)
    • [jvm-packages] Update kryo dependency to 2.22 (#4575)
    • [CI] Specify account ID when logging into ECR Docker registry (#4584)
    • Use Sphinx 2.1+ to compile documentation (#4609)
    • Make Pandas optional for running Python unit tests (#4620)
    • Fix spark tests on machines with many cores (#4634)
    • [jvm-packages] Update local dev build process (#4640)
    • Add optional dependencies to (#4655)
    • [jvm-packages] Fix maven warnings (#4664)
    • Remove extraneous files from the R package, to comply with CRAN policy (#4699)
    • Remove VC-2013 support, since it is not C++11 compliant (#4701)
    • [CI] Fix broken installation of Pandas (#4704, #4722)
    • [jvm-packages] Clean up temporary files afer running tests (#4706)
    • Specify version macro in CMake. (#4730)
    • Include dmlc-tracker into XGBoost Python package (#4731)
    • [CI] Use long key ID for Ubuntu repository fingerprints. (#4783)
    • Remove plugin, cuda related code in automake & autoconf files (#4789)
    • Skip related tests when scikit-learn is not installed. (#4791)
    • Ignore vscode and clion files (#4866)
    • Use bundled Google Test by default (#4900)
    • [CI] Raise timeout threshold in Jenkins (#4938)
    • Copy CMake parameter from dmlc-core. (#4948)
    • Set correct file permission. (#4964)
    • [CI] Update lint configuration to support latest pylint convention (#4971)
    • [CI] Upload nightly builds to S3 (#4976, #4979)
    • Add to cmake script. (#4999)
    • [CI] Fix Travis tests. (#5062)
    • [CI] Locate vcomp140.dll from System32 directory (#5078)
    • Implement training observer to dump internal states of objects (#5088). This will be useful for debugging.
    • Fix visual studio output library directories (#5119)
    • [jvm-packages] Comply with scala style convention + fix broken unit test (#5134)
    • [CI] Repair download URL for Maven 3.6.1 (#5139)
    • Don't use modernize-use-trailing-return-type in clang-tidy. (#5169)
    • Explicitly use UTF-8 codepage when using MSVC (#5197)
    • Add CMake option to run Undefined Behavior Sanitizer (UBSan) (#5211)
    • Make some GPU tests deterministic (#5229)
    • [R] Robust endian detection in CRAN xgboost build (#5232)
    • Support FreeBSD (#5233)
    • Make pip install xgboost*.tar.gz work by fixing (#5241)
    • Fix compilation error due to 64-bit integer narrowing to size_t (#5250)
    • Remove use of std::cout from R package, to comply with CRAN policy (#5261)
    • Update DMLC-Core submodule (#4674, #4688, #4726, #4924)
    • Update Rabit submodule (#4560, #4667, #4718, #4808, #4966, #5237)

    Usability Improvements, Documentation

    • Add Random Forest API to Python API doc (#4500)
    • Fix Python demo and doc. (#4545)
    • Remove doc about not supporting cuda 10.1 (#4578)
    • Address some sphinx warnings and errors, add doc for building doc. (#4589)
    • Add instruction to run formatting checks locally (#4591)
    • Fix docstring for XGBModel.predict() (#4592)
    • Doc and demo for customized metric and objective (#4598, #4608)
    • Add to documentation how to run tests locally (#4610)
    • Empty evaluation list in early stopping should produce meaningful error message (#4633)
    • Fixed year to 2019 in, helpers.h and LICENSE (#4661)
    • Minor updates to links and grammar (#4673)
    • Remove silent in doc (#4689)
    • Remove old Python trouble shooting doc (#4729)
    • Add os.PathLike support for file paths to DMatrix and Booster Python classes (#4757)
    • Update XGBoost4J-Spark doc (#4804)
    • Regular formatting for evaluation metrics (#4803)
    • [jvm-packages] Refine documentation for handling missing values in XGBoost4J-Spark (#4805)
    • Monitor for distributed envorinment (#4829). This is useful for identifying performance bottleneck.
    • Add check for length of weights and produce a good error message (#4872)
    • Fix DMatrix doc (#4884)
    • Export C++ headers in CMake installation (#4897)
    • Update license year in to 2019 (#4940)
    • Fix incorrectly displayed Note in the doc (#4943)
    • Follow PEP 257 Docstring Conventions (#4959)
    • Document minimum version required for Google Test (#5001)
    • Add better error message for invalid feature names (#5024)
    • Some guidelines on device memory usage (#5038)
    • [doc] Some notes for external memory. (#5065)
    • Update document for tree_method (#5106)
    • Update demo for ranking. (#5154)
    • Add new lines for Spark XGBoost missing values section (#5180)
    • Fix simple typo: utilty -> utility (#5182)
    • Update R doc by roxygen2 (#5201)
    • [R] Direct user to use set.seed() instead of setting seed parameter (#5125)
    • Add Optuna badge to (#5208)
    • Fix compilation error in c-api-demo.c (#5215)

    Known issues

    • When training parameter reg_lambda is set to zero, some leaf nodes may be assigned a NaN value. (See discussion) For now, please set reg_lambda to a nonzero value.
    • The initial 1.0.0 release of the Python package had a small bug that rendered it incompatible with Python 3.5. See #5328. If you are using Python 3.5, install 1.0.1 instead, by running
    pip3 install xgboost==1.0.1


    Contributors: Nan Zhu (@CodingCat), Crissman Loomis (@Crissman), Cyprien Ricque (@Cyprien-Ricque), Evan Kepner (@EvanKepner), K.O. (@Hi-king), KaiJin Ji (@KerryJi), Peter Badida (@KeyWeeUsr), Kodi Arfer (@Kodiologist), Rory Mitchell (@RAMitchell), Egor Smirnov (@SmirnovEgorRu), Jacob Kim (@TheJacobKim), Vibhu Jawa (@VibhuJawa), Marcos (@astrowonk), Andy Adinets (@canonizer), Chen Qin (@chenqin), Christopher Cowden (@cowden), @cpfarrell, @david-cortes, Liangcai Li (@firestarman), @fuhaoda, Philip Hyunsu Cho (@hcho3), @here-nagini, Tong He (@hetong007), Michal Kurka (@michalkurka), Honza Sterba (@honzasterba), @iblumin, @koertkuipers, mattn (@mattn), Mingjie Tang (@merlintang), OrdoAbChao (@mglowacki100), Matthew Jones (@mt-jones), mitama (@nigimitama), Nathan Moore (@nmoorenz), Daniel Stahl (@phillyfan1138), Michaël Benesty (@pommedeterresautee), Rong Ou (@rongou), Sebastian (@sfahnens), Xu Xiao (@sperlingxx), @sriramch, Sean Owen (@srowen), Stephanie Yang (@stpyang), Yuan Tang (@terrytangyuan), Mathew Wicks (@thesuperzapper), Tim Gates (@timgates42), TinkleG (@tinkle1129), Oleksandr Pryimak (@trams), Jiaming Yuan (@trivialfis), Matvey Turkov (@turk0v), Bobby Wang (@wbo4958), yage (@yage99), @yellowdolphin

    Reviewers: Nan Zhu (@CodingCat), Crissman Loomis (@Crissman), Cyprien Ricque (@Cyprien-Ricque), Evan Kepner (@EvanKepner), John Zedlewski (@JohnZed), KOLANICH (@KOLANICH), KaiJin Ji (@KerryJi), Kodi Arfer (@Kodiologist), Rory Mitchell (@RAMitchell), Egor Smirnov (@SmirnovEgorRu), Nikita Titov (@StrikerRUS), Jacob Kim (@TheJacobKim), Vibhu Jawa (@VibhuJawa), Andrew Kane (@ankane), Arno Candel (@arnocandel), Marcos (@astrowonk), Bryan Woods (@bryan-woods), Andy Adinets (@canonizer), Chen Qin (@chenqin), Thomas Franke (@coding-komek), Peter (@codingforfun), @cpfarrell, Joshua Patterson (@datametrician), @fuhaoda, Philip Hyunsu Cho (@hcho3), Tong He (@hetong007), Honza Sterba (@honzasterba), @iblumin, @jakirkham, Vadim Khotilovich (@khotilov), Keith Kraus (@kkraus14), @koertkuipers, @melonki, Mingjie Tang (@merlintang), OrdoAbChao (@mglowacki100), Daniel Mahler (@mhlr), Matthew Rocklin (@mrocklin), Matthew Jones (@mt-jones), Michaël Benesty (@pommedeterresautee), PSEUDOTENSOR / Jonathan McKinney (@pseudotensor), Rong Ou (@rongou), Vladimir (@sh1ng), Scott Lundberg (@slundberg), Xu Xiao (@sperlingxx), @sriramch, Pasha Stetsenko (@st-pasha), Stephanie Yang (@stpyang), Yuan Tang (@terrytangyuan), Mathew Wicks (@thesuperzapper), Theodore Vasiloudis (@thvasilo), TinkleG (@tinkle1129), Oleksandr Pryimak (@trams), Jiaming Yuan (@trivialfis), Bobby Wang (@wbo4958), yage (@yage99), @yellowdolphin, Yin Lou (@yinlou)

    Source code(tar.gz)
    Source code(zip)
  • v1.0.0rc2(Feb 14, 2020)

    Python package

    • Linux 64-bit wheel: xgboost-1.0.0rc2-py3-none-manylinux1_x86_64.whl
    • Windows 64-bit wheel: xgboost-1.0.0rc2-py3-none-win_amd64.whl
    • Source distribution: xgboost-1.0.0rc2.tar.gz

    R package: xgboost_1.0.0.1.tar.gz

    JVM packages (Linux 64-bit only)

    • XGBoost4J: xgboost4j_2.12-1.0.0-RC2.jar
    • XGBoost4J-Spark: xgboost4j-spark_2.12-1.0.0-RC2.jar
    • XGBoost4J-Flink: xgboost4j-flink_2.12-1.0.0-RC2.jar
    Source code(tar.gz)
    Source code(zip)
    xgboost-1.0.0rc2-py3-none-manylinux1_x86_64.whl(104.65 MB)
    xgboost-1.0.0rc2-py3-none-win_amd64.whl(23.42 MB)
    xgboost-1.0.0rc2.tar.gz(800.93 KB)
    xgboost4j-flink_2.12-1.0.0-RC2.jar(13.67 KB)
    xgboost4j-spark_2.12-1.0.0-RC2.jar(261.45 KB)
    xgboost4j_2.12-1.0.0-RC2.jar(2.04 MB)
    xgboost_1.0.0.1.tar.gz(705.78 KB)
  • v1.0.0rc1(Jan 31, 2020)

    Python package

    • Linux 64-bit wheel: xgboost-1.0.0rc1-py2.py3-none-manylinux1_x86_64.whl
    • Windows 64-bit wheel: xgboost-1.0.0rc1-py2.py3-none-win_amd64.whl
    • Source distribution: xgboost-1.0.0rc1.tar.gz

    R package: xgboost_1.0.0.1.tar.gz

    JVM packages (Linux 64-bit only)

    • XGBoost4J: xgboost4j_2.12-1.0.0-RC1.jar
    • XGBoost4J-Spark: xgboost4j-spark_2.12-1.0.0-RC1.jar
    • XGBoost4J-Flink: xgboost4j-flink_2.12-1.0.0-RC1.jar
    Source code(tar.gz)
    Source code(zip)
    xgboost-1.0.0rc1-py2.py3-none-manylinux1_x86_64.whl(104.65 MB)
    xgboost-1.0.0rc1-py2.py3-none-win_amd64.whl(23.42 MB)
    xgboost-1.0.0rc1.tar.gz(795.44 KB)
    xgboost4j-flink_2.12-1.0.0-RC1.jar(13.67 KB)
    xgboost4j-spark_2.12-1.0.0-RC1.jar(274.43 KB)
    xgboost4j_2.12-1.0.0-RC1.jar(2.03 MB)
    xgboost_1.0.0.1.tar.gz(705.07 KB)
  • v0.90(May 20, 2019)

    XGBoost Python package drops Python 2.x (#4379, #4381)

    Python 2.x is reaching its end-of-life at the end of this year. Many scientific Python packages are now moving to drop Python 2.x.

    XGBoost4J-Spark now requires Spark 2.4.x (#4377)

    • Spark 2.3 is reaching its end-of-life soon. See discussion at #4389.
    • Consistent handling of missing values (#4309, #4349, #4411): Many users had reported issue with inconsistent predictions between XGBoost4J-Spark and the Python XGBoost package. The issue was caused by Spark mis-handling non-zero missing values (NaN, -1, 999 etc). We now alert the user whenever Spark doesn't handle missing values correctly (#4309, #4349). See the tutorial for dealing with missing values in XGBoost4J-Spark. This fix also depends on the availability of Spark 2.4.x.

    Roadmap: better performance scaling for multi-core CPUs (#4310)

    • Poor performance scaling of the hist algorithm for multi-core CPUs has been under investigation (#3810). #4310 optimizes quantile sketches and other pre-processing tasks. Special thanks to @SmirnovEgorRu.

    Roadmap: Harden distributed training (#4250)

    • Make distributed training in XGBoost more robust by hardening Rabit, which implements the AllReduce primitive. In particular, improve test coverage on mechanisms for fault tolerance and recovery. Special thanks to @chenqin.

    New feature: Multi-class metric functions for GPUs (#4368)

    • Metrics for multi-class classification have been ported to GPU: merror, mlogloss. Special thanks to @trivialfis.
    • With supported metrics, XGBoost will select the correct devices based on your system and n_gpus parameter.

    New feature: Scikit-learn-like random forest API (#4148, #4255, #4258)

    • XGBoost Python package now offers XGBRFClassifier and XGBRFRegressor API to train random forests. See the tutorial. Special thanks to @canonizer

    New feature: use external memory in GPU predictor (#4284, #4396, #4438, #4457)

    • It is now possible to make predictions on GPU when the input is read from external memory. This is useful when you want to make predictions with big dataset that does not fit into the GPU memory. Special thanks to @rongou, @canonizer, @sriramch.

      dtest = xgboost.DMatrix('test_data.libsvm#dtest.cache')
      bst.set_param('predictor', 'gpu_predictor')
    • Coming soon: GPU training (gpu_hist) with external memory

    New feature: XGBoost can now handle comments in LIBSVM files (#4430)

    • Special thanks to @trivialfis and @hcho3

    New feature: Embed XGBoost in your C/C++ applications using CMake (#4323, #4333, #4453)

    • It is now easier than ever to embed XGBoost in your C/C++ applications. In your CMakeLists.txt, add xgboost::xgboost as a linked library:

      find_package(xgboost REQUIRED)
      add_executable(api-demo c-api-demo.c)
      target_link_libraries(api-demo xgboost::xgboost)

      XGBoost C API documentation is available. Special thanks to @trivialfis

    Performance improvements

    • Use feature interaction constraints to narrow split search space (#4341, #4428)
    • Additional optimizations for gpu_hist (#4248, #4283)
    • Reduce OpenMP thread launches in gpu_hist (#4343)
    • Additional optimizations for multi-node multi-GPU random forests. (#4238)
    • Allocate unique prediction buffer for each input matrix, to avoid re-sizing GPU array (#4275)
    • Remove various synchronisations from CUDA API calls (#4205)
    • XGBoost4J-Spark
      • Allow the user to control whether to cache partitioned training data, to potentially reduce execution time (#4268)


    • Fix node reuse in hist (#4404)
    • Fix GPU histogram allocation (#4347)
    • Fix matrix attributes not sliced (#4311)
    • Revise AUC and AUCPR metrics now work with weighted ranking task (#4216, #4436)
    • Fix timer invocation for InitDataOnce() in gpu_hist (#4206)
    • Fix R-devel errors (#4251)
    • Make gradient update in GPU linear updater thread-safe (#4259)
    • Prevent out-of-range access in column matrix (#4231)
    • Don't store DMatrix handle in Python object until it's initialized, to improve exception safety (#4317)
    • XGBoost4J-Spark
      • Fix non-deterministic order within a zipped partition on prediction (#4388)
      • Remove race condition on tracker shutdown (#4224)
      • Allow set the parameter maxLeaves. (#4226)
      • Allow partial evaluation of dataframe before prediction (#4407)
      • Automatically set maximize_evaluation_metrics if not explicitly given (#4446)

    API changes

    • Deprecate reg:linear in favor of reg:squarederror. (#4267, #4427)
    • Add attribute getter and setter to the Booster object in XGBoost4J (#4336)

    Maintenance: Refactor C++ code for legibility and maintainability

    • Fix clang-tidy warnings. (#4149)
    • Remove deprecated C APIs. (#4266)
    • Use Monitor class to time functions in hist. (#4273)
    • Retire DVec class in favour of c++20 style span for device memory. (#4293)
    • Improve HostDeviceVector exception safety (#4301)

    Maintenance: testing, continuous integration, build system

    • Major refactor of CMakeLists.txt (#4323, #4333, #4453): adopt modern CMake and export XGBoost as a target
    • Major improvement in Jenkins CI pipeline (#4234)
      • Migrate all Linux tests to Jenkins (#4401)
      • Builds and tests are now de-coupled, to test an artifact against multiple versions of CUDA, JDK, and other dependencies (#4401)
      • Add Windows GPU to Jenkins CI pipeline (#4463, #4469)
    • Support CUDA 10.1 (#4223, #4232, #4265, #4468)
    • Python wheels are now built with CUDA 9.0, so that JIT is not required on Volta architecture (#4459)
    • Integrate with NVTX CUDA profiler (#4205)
    • Add a test for cpu predictor using external memory (#4308)
    • Refactor tests to get rid of duplication (#4358)
    • Remove test dependency on craigcitro/r-travis, since it's deprecated (#4353)
    • Add files from local R build to .gitignore (#4346)
    • Make XGBoost4J compatible with Java 9+ by revising NativeLibLoader (#4351)
    • Jenkins build for CUDA 10.0 (#4281)
    • Remove remaining silent and debug_verbose in Python tests (#4299)
    • Use all cores to build XGBoost4J lib on linux (#4304)
    • Upgrade Jenkins Linux build environment to GCC 5.3.1, CMake 3.6.0 (#4306)
    • Make CMakeLists.txt compatible with CMake 3.3 (#4420)
    • Add OpenMP option in CMakeLists.txt (#4339)
    • Get rid of a few trivial compiler warnings (#4312)
    • Add external Docker build cache, to speed up builds on Jenkins CI (#4331, #4334, #4458)
    • Fix Windows tests (#4403)
    • Fix a broken python test (#4395)
    • Use a fixed seed to split data in XGBoost4J-Spark tests, for reproducibility (#4417)
    • Add additional Python tests to test training under constraints (#4426)
    • Enable building with shared NCCL. (#4447)

    Usability Improvements, Documentation

    • Document limitation of one-split-at-a-time Greedy tree learning heuristic (#4233)
    • Update build doc: PyPI wheel now support multi-GPU (#4219)
    • Fix docs for num_parallel_tree (#4221)
    • Fix document about colsample_by* parameter (#4340)
    • Make the train and test input with same colnames. (#4329)
    • Update R contribute link. (#4236)
    • Fix travis R tests (#4277)
    • Log version number in crash log in XGBoost4J-Spark (#4271, #4303)
    • Allow supression of Rabit output in Booster::train in XGBoost4J (#4262)
    • Add tutorial on handling missing values in XGBoost4J-Spark (#4425)
    • Fix typos (#4345, #4393, #4432, #4435)
    • Added language classifier in (#4327)
    • Added Travis CI badge (#4344)
    • Add BentoML to use case section (#4400)
    • Remove subtly sexist remark (#4418)
    • Add R vignette about parsing JSON dumps (#4439)


    Contributors: Nan Zhu (@CodingCat), Adam Pocock (@Craigacp), Daniel Hen (@Daniel8hen), Jiaxiang Li (@JiaxiangBU), Rory Mitchell (@RAMitchell), Egor Smirnov (@SmirnovEgorRu), Andy Adinets (@canonizer), Jonas (@elcombato), Harry Braviner (@harrybraviner), Philip Hyunsu Cho (@hcho3), Tong He (@hetong007), James Lamb (@jameslamb), Jean-Francois Zinque (@jeffzi), Yang Yang (@jokerkeny), Mayank Suman (@mayanksuman), jess (@monkeywithacupcake), Hajime Morrita (@omo), Ravi Kalia (@project-delphi), @ras44, Rong Ou (@rongou), Shaochen Shi (@shishaochen), Xu Xiao (@sperlingxx), @sriramch, Jiaming Yuan (@trivialfis), Christopher Suchanek (@wsuchy), Bozhao (@yubozhao)

    Reviewers: Nan Zhu (@CodingCat), Adam Pocock (@Craigacp), Daniel Hen (@Daniel8hen), Jiaxiang Li (@JiaxiangBU), Laurae (@Laurae2), Rory Mitchell (@RAMitchell), Egor Smirnov (@SmirnovEgorRu), @alois-bissuel, Andy Adinets (@canonizer), Chen Qin (@chenqin), Harry Braviner (@harrybraviner), Philip Hyunsu Cho (@hcho3), Tong He (@hetong007), @jakirkham, James Lamb (@jameslamb), Julien Schueller (@jschueller), Mayank Suman (@mayanksuman), Hajime Morrita (@omo), Rong Ou (@rongou), Sara Robinson (@sararob), Shaochen Shi (@shishaochen), Xu Xiao (@sperlingxx), @sriramch, Sean Owen (@srowen), Sergei Lebedev (@superbobry), Yuan (Terry) Tang (@terrytangyuan), Theodore Vasiloudis (@thvasilo), Matthew Tovbin (@tovbinm), Jiaming Yuan (@trivialfis), Xin Yin (@xydrolase)

    Source code(tar.gz)
    Source code(zip)
Distributed (Deep) Machine Learning Community
A Community of Awesome Machine Learning Projects
Distributed (Deep) Machine Learning Community
BLLIP reranking parser (also known as Charniak-Johnson parser, Charniak parser, Brown reranking parser) See for Python module.

BLLIP Reranking Parser Copyright Mark Johnson, Eugene Charniak, 24th November 2005 --- August 2006 We request acknowledgement in any publications that

Brown Laboratory for Linguistic Information Processing 214 Aug 15, 2022
Ingescape - Model-based framework for broker-free distributed software environments

Ingescape - Model-based framework for broker-free distributed software environments Overview Scope and Goals Ownership and License Dependencies with o

The ZeroMQ project 29 Aug 31, 2022
Edge ML Library - High-performance Compute Library for On-device Machine Learning Inference

Edge ML Library (EMLL) offers optimized basic routines like general matrix multiplications (GEMM) and quantizations, to speed up machine learning (ML) inference on ARM-based devices. EMLL supports fp32, fp16 and int8 data types. EMLL accelerates on-device NMT, ASR and OCR engines of Youdao, Inc.

NetEase Youdao 177 Sep 25, 2022
A lightweight C++ machine learning library for embedded electronics and robotics.

Fido Fido is an lightweight, highly modular C++ machine learning library for embedded electronics and robotics. Fido is especially suited for robotic

The Fido Project 412 Sep 19, 2022
A C++ standalone library for machine learning

Flashlight: Fast, Flexible Machine Learning in C++ Quickstart | Installation | Documentation Flashlight is a fast, flexible machine learning library w

Facebook Research 4.5k Oct 5, 2022
Flashlight is a C++ standalone library for machine learning

Flashlight is a fast, flexible machine learning library written entirely in C++ from the Facebook AI Research Speech team and the creators of Torch and Deep Speech.

null 4.5k Sep 29, 2022
ML++ - A library created to revitalize C++ as a machine learning front end

ML++ Machine learning is a vast and exiciting discipline, garnering attention from specialists of many fields. Unfortunately, for C++ programmers and

marc 1k Sep 22, 2022
A toolkit for making real world machine learning and data analysis applications in C++

dlib C++ library Dlib is a modern C++ toolkit containing machine learning algorithms and tools for creating complex software in C++ to solve real worl

Davis E. King 11.4k Oct 6, 2022
Samsung Washing Machine replacing OS control unit

hacksung Samsung Washing Machine WS1702 replacing OS control unit More info at

null 25 Sep 24, 2022
null 5.7k Oct 3, 2022
Machine Learning Framework for Operating Systems - Brings ML to Linux kernel

Machine Learning Framework for Operating Systems - Brings ML to Linux kernel

File systems and Storage Lab (FSL) 182 Aug 26, 2022
Distributed (Deep) Machine Learning Community 681 Aug 14, 2022
An SDL2-based implementation of OpenAL in a single C file.

MojoAL MojoAL is a full OpenAL 1.1 implementation, written in C, in a single source file. It uses Simple Directmedia Layer (SDL) 2.0 to handle much of

Ryan C. Gordon 88 Sep 13, 2022
C-based/Cached/Core Computer Vision Library, A Modern Computer Vision Library

Build Status Travis CI VM: Linux x64: Raspberry Pi 3: Jetson TX2: Backstory I set to build ccv with a minimalism inspiration. That was back in 2010, o

Liu Liu 6.9k Oct 1, 2022
MITIE: library and tools for information extraction

MITIE: MIT Information Extraction This project provides free (even for commercial use) state-of-the-art information extraction tools. The current rele

null 2.8k Oct 2, 2022
libsvm websitelibsvm - A simple, easy-to-use, efficient library for Support Vector Machines. [BSD-3-Clause] website

Libsvm is a simple, easy-to-use, and efficient software for SVM classification and regression. It solves C-SVM classification, nu-SVM classification,

Chih-Jen Lin 4.2k Oct 2, 2022
Open Source Computer Vision Library

OpenCV: Open Source Computer Vision Library Resources Homepage: Courses: Docs:

OpenCV 64.1k Oct 7, 2022
oneAPI Data Analytics Library (oneDAL)

Intel® oneAPI Data Analytics Library Installation | Documentation | Support | Examples | Samples | How to Contribute Intel® oneAPI Data Analytics Libr

oneAPI-SRC 520 Sep 26, 2022