dmlc/xgboost

Issues

• xgboost4j-spark-gpu train failed on multiple gpu node with EXCLUSIVE_PROCESS mode

  #11119 opened 7 days ago by yinqingh
  3

• CMake and CPU instructions docs

  #11121 opened 6 days ago by david-cortes
  3

• Inconsistent predictions

  #11120 opened 7 days ago by Hayakawa94
  2

• Does learning rate apply to linear booster?

  #11106 opened 10 days ago by david-cortes
  5

• Auto encoding for categorical data during inference.

  #11088 opened 15 days ago by trivialfis
  3

• Add support for Tweedie and Poisson regression for multi-output tasks

  #11110 opened 9 days ago by nickcorona
  1

• [QST] how to build xgboost in docker

  #11082 opened 10 days ago by wbo4958
  5

• Pred_contribs in 2.1.1 takes significantly more gpu memory than in 1.4.2

  #10936 opened 2 months ago by RostislavStoyanov
  6

• [CI] Threaded predict error.

  #11103 opened 11 days ago by trivialfis
  0

• Incompability between scikit-learn and xgboost

  #11093 opened 14 days ago by piotrjacak
  5

• Update R parameter constructor.

  #11083 opened 14 days ago by trivialfis
  5

• CI gpu iterator error.

  #11091 opened 14 days ago by trivialfis
  0

• [CI] 'DaskXGBClassifier' object has no attribute 'n_classes_'

  #11085 opened 15 days ago by hcho3
  6

• Crash when running XGBoost via PySpark (socket.cc - Check failed)

  #11067 opened 19 days ago by aardvarkk
  3

• DMatrix loader does not respect verbosity config

  #11075 opened 18 days ago by david-cortes
  0

• Test fails with Dask 2024.11.0+

  #10994 opened a month ago by hcho3
  4

• Use QDM automatically for the Dask interface.

  #10911 opened 20 days ago by trivialfis
  0

• Cost-Efficient Gradient Boosting (GreedyMiser) for XGBoost

  #11010 opened a month ago by eugeneyarovoi
  2

• 2.1.3 Patch release.

  #10992 opened 20 days ago by trivialfis
  4

• API: Custom objectives with zero hessian

  #11057 opened 20 days ago by DrumsnChocolate
  3

• Performance Issues with predict Call in XGBoost (v2.1.1)

  #11054 opened 22 days ago by isslerman
  1

• Two slightly different tarballs generated in release script; differentiate them

  #11045 opened 21 days ago by jakirkham
  9

• ValueError: could not convert string to float

  #11013 opened a month ago by Checunmily
  1

• [CI] group dependabot updates into fewer PRs and/or do not automatically run CI on them

  #11044 opened 23 days ago by jameslamb
  1

• ERROR : XGBoostError: XGBoost Library (libxgboost.so) could not be loaded

  #11048 opened 22 days ago by jeetendraswami5
  2

• Booster could have raw predictions for individual trees

  #11049 opened 22 days ago by david-cortes
  4

• [R] GC Torture test is very slow

  #11030 opened 23 days ago by david-cortes
  2

• [RFC] High-level interface for external memory.

  #11000 opened a month ago by trivialfis
  2

• [Question] Is it possible to get the name of the output classes of an XGBClassifier?

  #11024 opened a month ago by dhombios
  4

• Protobuf error.

  #11017 opened a month ago by trivialfis
  0

• [jvm-packages] the latest snapshot packages are broken

  #11015 opened a month ago by wbo4958
  1

• Python: Better xlabel in plot_importance()

  #11008 opened a month ago by mayer79
  2

• XGBoostj4-spark train: Failed to load xgboost4j library from jar

  #11011 opened a month ago by NvTimLiu
  1

• XGBoost Python API ignoring random state

  #10997 opened a month ago by mbarsacchi
  2

• discrete features with unique values < max_bin but with some values having very low frequency?

  #10999 opened a month ago by lukezli
  2

• Bug in `objective = "reg:pseudohubererror"` and `xgb.plot.tree()`

  #10988 opened 2 months ago by DrJerryTAO
  4

• PySpark params might be outdated.

  #10986 opened 2 months ago by trivialfis
  3

• Document is not clear on 'topk' and 'mean' for lambdarank_pair_method for lambda rank pair construction

  #10991 opened 2 months ago by nsh-bay
  1

• Add option to disable ELLPACK format/index arrays for GPU training

  #10981 opened 2 months ago by terraflops1048576
  3

• libomp: xgboost incorrect LC_RPATH referenced in libxgboost.dylib

  #10946 opened 2 months ago by Ubiquitous
  11

• xgboost Spark session not exiting after successful training run

  #10944 opened 2 months ago by jjayadeep06
  2

• XGBoostj4-spark train failed with spark version below than spark-3.5.0

  #10920 opened 2 months ago by NvTimLiu
  6

• Failed to bind socket. system error:Cannot assign requested address

  #10928 opened 2 months ago by alexdconf
  7

• CUDA virtual memory management with HOST NUMA might require special system capabilities.

  #10933 opened 2 months ago by trivialfis
  0

• XGBoostj4-spark train failed on the CPU hosts

  #10926 opened 2 months ago by NvTimLiu
  2

• Feature request - C API - support raw data as input for in-place prediction

  #10910 opened 2 months ago by tlkhm
  0

• Switching to float for histogram building

  #10913 opened 2 months ago by Shiki-H
  3

• The tracker may not pick up the correct network interface.

  #10897 opened 2 months ago by trivialfis
  3

• version 2.1.0, how to calculate model predict score from dump_model result。now, I use predict param output_margin=True and iteration_range=(0,1),but the result equal 1.56, boost[0] result is 0.0426801741, where is the gap

  #10915 opened 2 months ago by dulante00
  0

• Segmentation fault with enabled `lambdarank_unbiased` and `xgb_model` for training continuation

  #10905 opened 2 months ago by dgh0
  1