9adb812a0a
* [CI] Add RMM as an optional dependency * Replace caching allocator with pool allocator from RMM * Revert "Replace caching allocator with pool allocator from RMM" This reverts commit e15845d4e72e890c2babe31a988b26503a7d9038. * Use rmm::mr::get_default_resource() * Try setting default resource (doesn't work yet) * Allocate pool_mr in the heap * Prevent leaking pool_mr handle * Separate EXPECT_DEATH() in separate test suite suffixed DeathTest * Turn off death tests for RMM * Address reviewer's feedback * Prevent leaking of cuda_mr * Fix Jenkinsfile syntax * Remove unnecessary function in Jenkinsfile * [CI] Install NCCL into RMM container * Run Python tests * Try building with RMM, CUDA 10.0 * Do not use RMM for CUDA 10.0 target * Actually test for test_rmm flag * Fix TestPythonGPU * Use CNMeM allocator, since pool allocator doesn't yet support multiGPU * Use 10.0 container to build RMM-enabled XGBoost * Revert "Use 10.0 container to build RMM-enabled XGBoost" This reverts commit 789021fa31112e25b683aef39fff375403060141. * Fix Jenkinsfile * [CI] Assign larger /dev/shm to NCCL * Use 10.2 artifact to run multi-GPU Python tests * Add CUDA 10.0 -> 11.0 cross-version test; remove CUDA 10.0 target * Rename Conda env rmm_test -> gpu_test * Use env var to opt into CNMeM pool for C++ tests * Use identical CUDA version for RMM builds and tests * Use Pytest fixtures to enable RMM pool in Python tests * Move RMM to plugin/CMakeLists.txt; use PLUGIN_RMM * Use per-device MR; use command arg in gtest * Set CMake prefix path to use Conda env * Use 0.15 nightly version of RMM * Remove unnecessary header * Fix a unit test when cudf is missing * Add RMM demos * Remove print() * Use HostDeviceVector in GPU predictor * Simplify pytest setup; use LocalCUDACluster fixture * Address reviewers' commments Co-authored-by: Hyunsu Cho <chohyu01@cs.wasshington.edu>
28 lines
1.0 KiB
Python
28 lines
1.0 KiB
Python
import xgboost as xgb
|
|
from sklearn.datasets import make_classification
|
|
import dask
|
|
from dask.distributed import Client
|
|
from dask_cuda import LocalCUDACluster
|
|
|
|
def main(client):
|
|
X, y = make_classification(n_samples=10000, n_informative=5, n_classes=3)
|
|
X = dask.array.from_array(X)
|
|
y = dask.array.from_array(y)
|
|
dtrain = xgb.dask.DaskDMatrix(client, X, label=y)
|
|
|
|
params = {'max_depth': 8, 'eta': 0.01, 'objective': 'multi:softprob', 'num_class': 3,
|
|
'tree_method': 'gpu_hist'}
|
|
output = xgb.dask.train(client, params, dtrain, num_boost_round=100,
|
|
evals=[(dtrain, 'train')])
|
|
bst = output['booster']
|
|
history = output['history']
|
|
for i, e in enumerate(history['train']['merror']):
|
|
print(f'[{i}] train-merror: {e}')
|
|
|
|
if __name__ == '__main__':
|
|
# To use RMM pool allocator with a GPU Dask cluster, just add rmm_pool_size option to
|
|
# LocalCUDACluster constructor.
|
|
with LocalCUDACluster(rmm_pool_size='2GB') as cluster:
|
|
with Client(cluster) as client:
|
|
main(client)
|