Jiaming Yuan 01c4711556

Check __cuda_array_interface__ instead of cupy class. (#9971) ...

* Now XGBoost can directly consume CUDA data from torch.

2024-01-09 19:59:01 +08:00

..

dask

Check __cuda_array_interface__ instead of cupy class. (#9971)

2024-01-09 19:59:01 +08:00

spark

Cleanup code for distributed training. (#9805)

2023-11-25 09:10:56 +08:00

testing

Synthesize the AMES housing dataset for tests. (#9963)

2024-01-09 00:54:23 +08:00

__init__.py

Remove the deprecated Python rabit module. (#9523)

2023-08-27 03:37:05 +08:00

_typing.py

Use weakref instead of id for DataIter cache. (#9445)

2023-08-10 00:40:06 +08:00

callback.py

Use UBJ in Python checkpoint. (#9958)

2024-01-09 03:22:15 +08:00

collective.py

Use dlopen to load NCCL. (#9796)

2023-11-22 19:27:31 +08:00

compat.py

Check __cuda_array_interface__ instead of cupy class. (#9971)

2024-01-09 19:59:01 +08:00

config.py

Replace setup.py with pyproject.toml (#9021)

2023-04-20 13:51:39 -07:00

core.py

Check __cuda_array_interface__ instead of cupy class. (#9971)

2024-01-09 19:59:01 +08:00

data.py

Check __cuda_array_interface__ instead of cupy class. (#9971)

2024-01-09 19:59:01 +08:00

federated.py

Allow insecure gRPC connections for federated learning (#8181)

2022-08-19 12:16:14 +08:00

libpath.py

Fix libpath logic for Windows (#9712)

2023-10-24 17:25:28 -07:00

plotting.py

Replace setup.py with pyproject.toml (#9021)

2023-04-20 13:51:39 -07:00

py.typed

[dask] Add type hints. (#6519)

2020-12-29 19:41:02 +08:00

sklearn.py

Check __cuda_array_interface__ instead of cupy class. (#9971)

2024-01-09 19:59:01 +08:00

tracker.py

[rabit] Small cleanup to tracker initialization. (#9524)

2023-08-27 05:10:59 +08:00

training.py

Use matrix for gradient. (#9508)

2023-08-24 05:29:52 +08:00

VERSION

Bump version to 2.1. (#9498)

2023-08-18 01:04:04 +08:00