Hendrik/xgboost
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
7,065 Commits 32 Branches 59 Tags
Commit Graph

1794 Commits

Author SHA1 Message Date
Jiaming Yuan
ea0deeca68
Disable dense optimization in hist for distributed training. (#9272) 2023-06-10 02:31:34 +08:00
Jiaming Yuan
1fcc26a6f8
Set ndcg to default for LTR. (#8822) 
- Add document.
- Add tests.
- Use `ndcg` with `topk` as default.
 2023-06-09 23:31:33 +08:00
Rong Ou
ff122d61ff
More tests for cpu predictor with column split (#9270) 2023-06-08 22:47:19 +08:00
ZHAOKAI WANG
84d3fcb7ea
Fix cpu_predictor categorical feature disaptch (#9256) 2023-06-08 01:24:04 +08:00
amdsc21
35cde3b1b2 remove some hip.h 2023-06-07 04:48:09 +02:00
amdsc21
ce345c30a8 remove some hip.h 2023-06-07 03:39:01 +02:00
amdsc21
af8845405a sync Jun 5 2023-06-07 02:43:21 +02:00
Jiaming Yuan
0cba2cdbb0
Support linalg data structures in check device. (#9243) 2023-06-06 09:47:24 +08:00
Rong Ou
962a20693f
More support for column split in cpu predictor (#9244) 
- Added column split support to `PredictInstance` and `PredictLeaf`.
- Refactoring of tests.
 2023-06-05 08:05:38 +08:00
Jiaming Yuan
9fbde21e9d
Rework the precision metric. (#9222) 
- Rework the precision metric for both CPU and GPU.
- Mention it in the document.
- Cleanup old support code for GPU ranking metric.
- Deterministic GPU implementation.

* Drop support for classification.

* type.

* use batch shape.

* lint.

* cpu build.

* cpu build.

* lint.

* Tests.

* Fix.

* Cleanup error message.
 2023-06-02 20:49:43 +08:00
amdsc21
9ee1852d4e restore device helper 2023-06-02 02:55:13 +02:00
Your Name
42867a4805 sync Jun 1 2023-06-01 15:55:06 -07:00
ZHAOKAI WANG
fa2ab1f021
TreeRefresher note word spelling modification (#9223) 2023-05-31 20:27:27 +08:00
Jiaming Yuan
17fd3f55e9
Optimize adapter element counting on GPU. (#9209) 
- Implement a simple `IterSpan` for passing iterators with size.
- Use shared memory for column size counts.
- Use one thread for each sample in row count to reduce atomic operations.
 2023-05-30 23:28:43 +08:00
Jiaming Yuan
097f11b6e0
Support CUDA f16 without transformation. (#9207) 
- Support f16 from cupy.
- Include CUDA header explicitly.
- Cleanup cmake nvtx support.
 2023-05-30 20:54:31 +08:00
Jiaming Yuan
ae7450ce54
Skip optional synchronization in thrust. (#9212) 2023-05-30 17:23:09 +08:00
Jiaming Yuan
03bc6e6427
Remove unused variables. (#9210) 
- remove used variables.
- Remove signed comparison warnings.
 2023-05-28 05:24:15 +08:00
Jiaming Yuan
053aababd4
Avoid thrust logical operation. (#9199) 
Thrust implementation of `thrust::all_of/any_of/none_of` adopts an early stopping strategy
to bailout early by dividing the input into small batches. This is not ideal for data
validation as we expect all data to be valid. The strategy leads to excessive kernel
launches and stream synchronization.

* Use reduce from dh instead.
 2023-05-27 01:36:58 +08:00
Rong Ou
5b69534b43
Support column split in multi-target hist (#9171) 2023-05-26 16:56:05 +08:00
Rong Ou
acd363033e
Fix running MGPU gtests (#9200) 2023-05-26 05:26:38 +08:00
amdsc21
3a834c4992 change workflow 2023-05-20 07:04:06 +02:00
amdsc21
b22644fc10 add hip.h 2023-05-20 01:25:33 +02:00
amdsc21
8cad8c693c sync up May15 2023 2023-05-15 18:59:18 +02:00
Stephan T. Lavavej
7375bd058b
Fix IndexTransformIter. (#9155) 2023-05-12 21:25:54 +08:00
Stephan T. Lavavej
779b82c098
Avoid redefining macros. (#9154) 2023-05-11 15:59:25 -07:00
Rong Ou
603f8ce2fa
Support hist in the partition builder under column split (#9120) 2023-05-11 05:24:29 +08:00
Rong Ou
52311dcec9
Fix multi-threaded gtests (#9148) 2023-05-10 19:15:32 +08:00
Jiaming Yuan
85988a3178
Wait for data CUDA stream instead of sync. (#9144) 
---------

Co-authored-by: Philip Hyunsu Cho <chohyu01@cs.washington.edu>
 2023-05-09 09:52:21 +08:00
Jiaming Yuan
55968ed3fa
Fix monotone constraints on CPU. (#9122) 2023-05-06 01:07:54 +08:00
amdsc21
b066accad6 fix lambdarank_obj 2023-05-02 21:06:22 +02:00
amdsc21
b324d51f14 fix array_interface.h half type 2023-05-02 20:50:50 +02:00
amdsc21
65097212b3 fix IterativeDeviceDMatrix, support HIP 2023-05-02 20:20:11 +02:00
amdsc21
83e6fceb5c fix lambdarank_obj.cc, support HIP 2023-05-02 19:03:18 +02:00
amdsc21
e4538cb13c fix, to support hip 2023-05-02 17:43:11 +02:00
amdsc21
5446c501af merge 23Mar01 2023-05-02 00:05:58 +02:00
amdsc21
313a74b582 add Shap Magic to check if use cat 2023-05-01 21:55:14 +02:00
Jiaming Yuan
08ce495b5d
Use Booster context in DMatrix. (#8896) 
- Pass context from booster to DMatrix.
- Use context instead of integer for `n_threads`.
- Check the consistency configuration for `max_bin`.
- Test for all combinations of initialization options.
 2023-04-28 21:47:14 +08:00
Jiaming Yuan
1f9a57d17b
[Breaking] Require format to be specified in input URI. (#9077) 
Previously, we use `libsvm` as default when format is not specified. However, the dmlc
data parser is not particularly robust against errors, and the most common type of error
is undefined format.

Along with which, we will recommend users to use other data loader instead. We will
continue the maintenance of the parsers as it's currently used for many internal tests
including federated learning.
 2023-04-28 19:45:15 +08:00
Jiaming Yuan
17ff471616
Optimize array interface input. (#9090) 2023-04-28 18:01:58 +08:00
Jiaming Yuan
e206b899ef
Rework MAP and Pairwise for LTR. (#9075) 2023-04-28 02:39:12 +08:00
Jiaming Yuan
0e470ef606
Optimize prediction with QuantileDMatrix. (#9096) 
- Reduce overhead in `FVecDrop`.
- Reduce overhead caused by `HostVector()` calls.
 2023-04-28 00:51:41 +08:00
Rong Ou
a320b402a5
More refactoring to take advantage of collective aggregators (#9081) 2023-04-26 03:36:09 +08:00
Rong Ou
8dbe0510de
More collective aggregators (#9060) 2023-04-22 03:32:05 +08:00
Jiaming Yuan
7032981350
Fix timer annotation. (#9057) 2023-04-21 22:53:58 +08:00
Jiaming Yuan
b908680bec
Fix race condition in cpp metric tests. (#9058) 2023-04-21 05:24:10 +08:00
Jiaming Yuan
a7b3dd3176
Fix compiler warnings. (#9055) 2023-04-21 02:26:47 +08:00
amdsc21
65d83e288f fix device query 2023-04-19 19:53:26 +02:00
Rong Ou
42d100de18
Make sure metrics work with federated learning (#9037) 2023-04-19 15:39:11 +08:00
Jiaming Yuan
ef13dd31b1
Rework the NDCG objective. (#9015) 2023-04-18 21:16:06 +08:00
Rong Ou
ba9d24ff7b
Make sure metrics work with column-wise distributed training (#9020) 2023-04-18 03:48:23 +08:00