523 Commits

Author SHA1 Message Date
Jiaming Yuan
a7226c0222
Fix feature names with special characters. (#9923) 2023-12-28 22:45:13 +08:00
Jiaming Yuan
faf0f2df10
Support dataframe data format in native XGBoost. (#9828)
- Implement a columnar adapter.
- Refactor Python pandas handling code to avoid converting into a single numpy array.
- Add support in R for transforming columns.
- Support R data.frame and factor type.
2023-12-12 09:56:31 +08:00
Jiaming Yuan
42de9206fc
Support multi-target, fit intercept for hinge. (#9850) 2023-12-08 05:50:41 +08:00
Jiaming Yuan
39c637ee19
Use array interface in Python prediction return. (#9855) 2023-12-08 03:42:14 +08:00
Dmitry Razdoburdin
381f1d3dc9
Add support inference on SYCL devices (#9800)
---------

Co-authored-by: Dmitry Razdoburdin <>
Co-authored-by: Nikolay Petrov <nikolay.a.petrov@intel.com>
Co-authored-by: Alexandra <alexandra.epanchinzeva@intel.com>
2023-12-04 16:15:57 +08:00
Jiaming Yuan
8fe1a2213c
Cleanup code for distributed training. (#9805)
* Cleanup code for distributed training.

- Merge `GetNcclResult` into nccl stub.
- Split up utilities from the main dask module.
- Let Channel return `Result` to accommodate nccl channel.
- Remove old `use_label_encoder` parameter.
2023-11-25 09:10:56 +08:00
Jiaming Yuan
0715ab3c10
Use dlopen to load NCCL. (#9796)
This PR adds optional support for loading nccl with `dlopen` as an alternative of compile time linking. This is to address the size bloat issue with the PyPI binary release.
- Add CMake option to load `nccl` at runtime.
- Add an NCCL stub.

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

At the moment, this is Linux only since we only support MNMG on Linux.
2023-11-22 19:27:31 +08:00
Jiaming Yuan
fedd9674c8
Implement column sampler in CUDA. (#9785)
- CUDA implementation.
- Extract the broadcasting logic, we will need the context parameter after revamping the collective implementation.
- Some changes to the event loop for fixing a deadlock in CI.
- Move argsort into algorithms.cuh, add support for cuda stream.
2023-11-17 04:29:08 +08:00
Jiaming Yuan
44099f585d
[coll] Add C API for the tracker. (#9773) 2023-11-08 18:17:14 +08:00
Jiaming Yuan
06bdc15e9b
[coll] Pass context to various functions. (#9772)
* [coll] Pass context to various functions.

In the future, the `Context` object would be required for collective operations, this PR
passes the context object to some required functions to prepare for swapping out the
implementation.
2023-11-08 09:54:05 +08:00
Jiaming Yuan
4da4e092b5
[coll] Improvements and fixes for tracker and allreduce. (#9745)
- Allow the tracker to wait.
- Fix allreduce type cast
- Return args from the federated tracker.
2023-11-02 04:06:46 +08:00
Jiaming Yuan
bc995a4865
[coll] Add federated coll. (#9738)
- Define a new data type, the proto file is copied for now.
- Merge client and communicator into `FederatedColl`.
- Define CUDA variant.
- Migrate tests for CPU, add tests for CUDA.
2023-11-01 04:06:46 +08:00
Jiaming Yuan
6755179e77
[coll] Add nccl. (#9726) 2023-10-28 16:33:58 +08:00
Jiaming Yuan
7a02facc9d
Serialize expand entry for allgather. (#9702) 2023-10-24 14:33:28 +08:00
Philip Hyunsu Cho
3b86260b50
Fix build for AppleClang 11 (#9684) (#9693) 2023-10-18 12:27:21 -07:00
Jiaming Yuan
5d1bcde719
[coll] allgatherv. (#9688) 2023-10-19 03:13:50 +08:00
Dmitry Razdoburdin
ea9f09716b
Reorder if-else statements to allow using of cpu branches for sycl-devices (#9682) 2023-10-18 10:55:33 +08:00
Jiaming Yuan
53049b16b8
[coll] Broadcast. (#9659) 2023-10-14 09:34:37 +08:00
Jiaming Yuan
084d89216c
Add support for cgroupv2. (#9651) 2023-10-12 09:36:36 +08:00
Jiaming Yuan
680d53db43
Extract JSON utils. (#9645) 2023-10-10 07:15:14 +08:00
Jiaming Yuan
417c3ba47e
Workaround Apple clang issue. (#9615) 2023-09-28 22:51:47 +08:00
Rong Ou
def77870f3
Test categorical features with column-split gpu quantile (#9595) 2023-09-23 09:55:09 +08:00
Jiaming Yuan
8c676c889d
Remove internal use of gpu_id. (#9568) 2023-09-20 23:29:51 +08:00
Jiaming Yuan
adea842c83
Fix inplace predict with fallback when base margin is used. (#9536)
- Copy meta info from proxy DMatrix.
- Use `std::call_once` to emit less warnings.
2023-09-05 01:04:24 +08:00
Jiaming Yuan
ddf2e68821
Use the new DeviceOrd in the linalg module. (#9527) 2023-08-29 13:37:29 +08:00
Jiaming Yuan
942b957eef
Fix GPU categorical split memory allocation. (#9529) 2023-08-29 10:06:03 +08:00
Jiaming Yuan
044fea1281
Drop support for loading remote files. (#9504) 2023-08-21 23:34:05 +08:00
Jiaming Yuan
05d7000096
Handle special characters in JSON model dump. (#9474) 2023-08-14 15:49:00 +08:00
Jiaming Yuan
bb56183396
Normalize file system path. (#9463) 2023-08-11 21:26:46 +08:00
Jiaming Yuan
1caa93221a
Use realloc for histogram cache and expose the cache limit. (#9455) 2023-08-10 14:05:27 +08:00
Jiaming Yuan
f05a23b41c
Use weakref instead of id for DataIter cache. (#9445)
- Fix case where Python reuses id from freed objects.
- Small optimization to column matrix with QDM by using `realloc` instead of copying data.
2023-08-10 00:40:06 +08:00
Jiaming Yuan
f05294a6f2
Fix clang warnings. (#9447)
- static function in header. (which is marked as unused due to translation unit
visibility).
- Implicit copy operator is deprecated.
- Unused lambda capture.
- Moving a temporary variable prevents copy elision.
2023-08-09 15:34:45 +08:00
Philip Hyunsu Cho
7ce090e775
Handle UTF-8 paths correctly on Windows platform (#9443)
* Fix round-trip serialization with UTF-8 paths

* Add compiler version check

* Add comment to C API functions

* Add Python tests

* [CI] Updatre MacOS deployment target

* Use std::filesystem instead of dmlc::TemporaryDirectory
2023-08-07 23:27:25 -07:00
Jiaming Yuan
97fd5207dd
Use lambda function in ParallelFor2D. (#9441) 2023-08-08 14:04:46 +08:00
Jiaming Yuan
54029a59af
Bound the size of the histogram cache. (#9440)
- A new histogram collection with a limit in size.
- Unify histogram building logic between hist, multi-hist, and approx.
2023-08-08 03:21:26 +08:00
Jiaming Yuan
1332ff787f
Unify the code path between local and distributed training. (#9433)
This removes the need for a local histogram space during distributed training, which cuts the cache size by half.
2023-08-03 21:46:36 +08:00
Jiaming Yuan
e93a274823
Small cleanup for histogram routines. (#9427)
* Small cleanup for histogram routines.

- Extract hist train param from GPU hist.
- Make histogram const after construction.
- Unify parameter names.
2023-08-02 18:28:26 +08:00
Jiaming Yuan
912e341d57
Initial GPU support for the approx tree method. (#9414) 2023-07-31 15:50:28 +08:00
Rong Ou
7579905e18
Retry switching to per-thread default stream (#9416) 2023-07-26 07:09:12 +08:00
Jiaming Yuan
3a9996173e
Revert "Switch to per-thread default stream (#9396)" (#9413)
This reverts commit f7f673b00c15458fb4dd74a2a0d2ba80369c5faf.
2023-07-24 12:03:28 -07:00
Jiaming Yuan
a196443a07
Implement sketching with Hessian on GPU. (#9399)
- Prepare for implementing approx on GPU.
- Unify the code path between weighted and uniform sketching on DMatrix.
2023-07-24 15:43:03 +08:00
Jiaming Yuan
22b0a55a04
Remove hist builder class. (#9400)
* Remove hist build class.

* Cleanup this stateless class.

* Add comment to thread block.
2023-07-22 10:43:12 +08:00
Jiaming Yuan
dbd5309b55
Fix warning message for device. (#9402) 2023-07-20 23:30:04 +08:00
Rong Ou
f7f673b00c
Switch to per-thread default stream (#9396) 2023-07-20 08:21:00 +08:00
Jiaming Yuan
0a07900b9f
Fix integer overflow. (#9380) 2023-07-15 21:11:02 +08:00
Jiaming Yuan
16eb41936d
Handle the new device parameter in dask and demos. (#9386)
* Handle the new `device` parameter in dask and demos.

- Check no ordinal is specified in the dask interface.
- Update demos.
- Update dask doc.
- Update the condition for QDM.
2023-07-15 19:11:20 +08:00
Jiaming Yuan
04aff3af8e
Define the new device parameter. (#9362) 2023-07-13 19:30:25 +08:00
Rong Ou
3632242e0b
Support column split with GPU quantile (#9370) 2023-07-11 12:15:56 +08:00
Jiaming Yuan
97ed944209
Unify the hist tree method for different devices. (#9363) 2023-07-11 10:04:39 +08:00
Jiaming Yuan
20c52f07d2
Support exporting cut values (#9356) 2023-07-08 15:32:41 +08:00