NVIDIA/cuml

NVIDIA cuML: GPU-Accelerated Machine Learning

Stars: 5.3k
Forks: 680
Open beginner issues: 4
Indexed issues: 757
Avg merge: 1d 11h
Merged PRs (30d): 103

Dominant language: Python
License: Apache-2.0
Last GitHub push: Sep 18, 2026
Latest indexed: Sep 19, 2026
Contributing guide: Contributing guide
Code of conduct: No code of conduct
Beginner labels: good first issue

Beginner friendly Everything

Open All

[FEA] Warp-aggregate same-address atomics in t-SNE attractive-force kernels Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

NVIDIA/cuml#8707 · Opened Sep 23, 2026
[BUG] Unintended FP64 promotion in float kernels of UMAP, t-SNE and HDBSCAN Open

Difficulty 3/5 1-2 days Newbie friendliness 45/100

NVIDIA/cuml#8706 · Opened Sep 23, 2026
[BUG] libcuml fails to build with -DCUML_ALGORITHMS=SVM (cuVS not linked) Open

Difficulty 2/5 1-3 hours Newbie friendliness 65/100

NVIDIA/cuml#8705 · Opened Sep 23, 2026
Remove deprecated `cuml.tsa` module Open

NVIDIA/cuml#8703 · 1 assignee · Opened Sep 23, 2026
[BUG] `TargetEncoder` treats a fitted `None` category as unseen during `transform` Open

? - Needs Triage bug

Difficulty 3/5 1-2 days Newbie friendliness 65/100

NVIDIA/cuml#8697 · 1 comment · Opened Sep 23, 2026
[BUG] `PolynomialFeatures(degree=0)` fails during transform with a broadcasting error Open

? - Needs Triage bug

Difficulty 3/5 1-2 days Newbie friendliness 72/100

NVIDIA/cuml#8694 · 1 comment · Opened Sep 22, 2026
[CI] QuantileTransformer tests fail against scikit-learn 1.10.dev0 Open

NVIDIA/cuml#8693 · 1 assignee · Opened Sep 22, 2026
Flaky `test_kmeans_device_buffer_samples_host_path` inertia check Open

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

NVIDIA/cuml#8692 · 1 comment · Opened Sep 22, 2026
[FEA] Expose merge distances in cuml.cluster.AgglomerativeClustering Open

feature request

Difficulty 4/5 3-5 days Newbie friendliness 55/100

NVIDIA/cuml#8684 · 2 comments · 1 assignee · Opened Sep 19, 2026
[BUG] CI test failure with `test_standardization_sparse_with_shift_scale` Open

? - Needs Triage bug

Difficulty 3/5 1-2 days Newbie friendliness 35/100

NVIDIA/cuml#8682 · Opened Sep 18, 2026
[BUG] `KBinsDiscretizer` with per-feature `n_bins` fails because validation accesses removed `cupy.int` alias Open

? - Needs Triage bug

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

NVIDIA/cuml#8678 · 1 comment · Opened Sep 18, 2026
[Proposal] Remove the abandoned cuml::genetic implementation Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

NVIDIA/cuml#8675 · 1 comment · 2 reactions · Opened Sep 18, 2026
[BUG] `kneighbors_graph` silently ignores `Minkowski` feature weights in `metric_params` Open

bug

NVIDIA/cuml#8643 · 1 comment · 1 assignee · Opened Sep 15, 2026
[BUG] `ComplementNB` fails with an ambiguous truth-value error for per-feature `alpha` Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 65/100

NVIDIA/cuml#8642 · Opened Sep 15, 2026
[FEA] Add a repository-grounded cuML agent skill Open

Difficulty 4/5 3-5 days Newbie friendliness 45/100

NVIDIA/cuml#8638 · 3 comments · Opened Sep 14, 2026
[BUG] `StratifiedKFold` rejects single-class targets that scikit-learn splits successfully Open

bug

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

NVIDIA/cuml#8632 · Opened Sep 13, 2026
[BUG] `Lars` produces incorrect coefficients, intercept, predictions, and score on a simple exact linear dataset Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 72/100

NVIDIA/cuml#8630 · Opened Sep 13, 2026
[FEA] Make distributed RF sampler to draw from a global cdf Open

algo: random-forest Dask / cuml.dask feature request

NVIDIA/cuml#8628 · 1 assignee · Opened Sep 12, 2026
[BUG] `ColumnTransformer.set_params` rejects nested transformer parameters Open

bug

Difficulty 3/5 1-2 days Newbie friendliness 76/100

NVIDIA/cuml#8626 · Opened Sep 11, 2026
[Tracker] Track nightly and CI failures for the 26.12 development cycle Open

Difficulty 3/5 1-2 days Newbie friendliness 30/100

NVIDIA/cuml#8620 · Opened Sep 11, 2026
Modernize the cuML C++ API Open

Difficulty 5/5 Over a week Newbie friendliness 30/100

NVIDIA/cuml#8591 · 1 reaction · Opened Sep 9, 2026
[BUG] `ColumnTransformer` with `Normalizer(norm="l1")` produces L2-normalized values Open

bug

NVIDIA/cuml#8577 · 2 comments · 1 assignee · Opened Sep 9, 2026
[BUG] `AgglomerativeClustering` rejects finite `float64` values after overflowing them during conversion to `float32` Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 68/100

NVIDIA/cuml#8570 · 1 comment · Opened Sep 8, 2026
[BUG] `SpectralClustering` with `nearest_neighbors` returns one cluster when `n_clusters=2` Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 52/100

NVIDIA/cuml#8569 · 1 comment · Opened Sep 8, 2026
[BUG] `EmpiricalCovariance` produces an unstable precision matrix and incorrect Mahalanobis distances for singular covariance Open

bug

Difficulty 4/5 3-5 days Newbie friendliness 68/100

NVIDIA/cuml#8566 · 1 comment · Opened Sep 7, 2026
[DOC] Implement link checking with `lychee` in CI Open

doc

NVIDIA/cuml#8543 · 1 assignee · Opened Sep 1, 2026
[Tracker] Track nightly and CI failures for the 26.10 development cycle Open

bug ci

NVIDIA/cuml#8527 · 1 comment · 1 assignee · Opened Aug 26, 2026
[DOC] Improve and publish the cuML changelog Open

doc

NVIDIA/cuml#8521 · 6 comments · 1 assignee · Opened Aug 25, 2026
Add cuml.accel support for OrdinalEncoder Open

cuml-accel

NVIDIA/cuml#8515 · 1 assignee · Opened Aug 24, 2026
[FEA] Add native GPU Gradient Boosting (GBM) estimators to cuML Open

feature request

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA/cuml#8506 · 2 comments · Opened Aug 24, 2026
[FEA] LocalOutlierFactor Open

Difficulty 3/5 1-2 days Newbie friendliness 72/100

NVIDIA/cuml#8504 · 1 comment · Opened Aug 24, 2026
[BUG] `make_column_transformer` fails on a two-dimensional Python list input Open

bug Cython / Python sklearn-api-compat

NVIDIA/cuml#8502 · 1 comment · 1 assignee · Opened Aug 22, 2026
[FEA] Support `oob_prediction_` / `oob_decision_function_` in Dask RandomForest Open

algo: random-forest Dask / cuml.dask feature request

Difficulty 4/5 3-5 days Newbie friendliness 48/100

NVIDIA/cuml#8501 · Opened Aug 21, 2026
Introduce a declarative parameter validation framework for estimators Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA/cuml#8498 · 1 comment · Opened Aug 20, 2026
[BUG] single_linkage aborts on unsupported DistanceType instead of rejecting it Open

benchmarking bug CUDA / C++ Cython / Python libcuml sklearn-api-compat

Difficulty 3/5 1-2 days Newbie friendliness 68/100

NVIDIA/cuml#8497 · Opened Aug 20, 2026
[BUG] sg_benchmark segfaults in fixture data allocation Open

benchmarking bug CUDA / C++ libcuml

Difficulty 4/5 3-5 days Newbie friendliness 72/100

NVIDIA/cuml#8496 · Opened Aug 20, 2026
[BUG] `SpectralClustering` with `affinity="precomputed"` causes segmentation fault Open

algo: spectral-embedding bug

Difficulty 4/5 3-5 days Newbie friendliness 50/100

NVIDIA/cuml#8492 · 3 comments · 1 assignee · Opened Aug 19, 2026
Complete the IsolationForest Treelite integration Open

NVIDIA/cuml#8488 · 1 comment · 1 assignee · Opened Aug 18, 2026
[DOC] Document nvdashboard jupyterlab toggle accelerator for cudf.accel Open

doc

NVIDIA/cuml#8469 · 2 comments · 1 assignee · Opened Aug 11, 2026
[BUG] RF max_leaves uses FIFO growth instead of best-first growth Open

NVIDIA/cuml#8461 · 1 assignee · Opened Aug 7, 2026
[CI] RandomForestRegressor sklearn compatibility check is flaky Open

bug ci

Difficulty 3/5 1-2 days Newbie friendliness 58/100

NVIDIA/cuml#8457 · Opened Aug 5, 2026
[CI] Remove xgboost future warning filter Open

bug ci

NVIDIA/cuml#8454 · 1 assignee · Opened Aug 5, 2026
Require benchmark coverage declarations for new cuML estimators Open

Difficulty 4/5 3-5 days Newbie friendliness 55/100

NVIDIA/cuml#8434 · 1 reaction · Opened Aug 3, 2026
Add a native cuML capabilities overview Open

Difficulty 5/5 Over a week Newbie friendliness 35/100

NVIDIA/cuml#8428 · Opened Jul 30, 2026
Isolation Forest follow-up work Open

NVIDIA/cuml#8420 · 10 comments · 1 assignee · Opened Jul 29, 2026
Decide how to handle non-deterministic t-SNE algorithms Open

algo: tsne CUDA / C++

Difficulty 5/5 Over a week Newbie friendliness 25/100

NVIDIA/cuml#8418 · Opened Jul 29, 2026
[cuml.accel] Remove `strict: false` in `test_voting::test_sample_weight[42]` XFAIL Open

Difficulty 3/5 1-2 days Newbie friendliness 64/100

NVIDIA/cuml#8407 · Opened Jul 25, 2026
Drop `numba`/`numba.cuda` as a required dependency Open

NVIDIA/cuml#8380 · 1 comment · 1 assignee · Opened Jul 14, 2026
Fix threshold in `MBSGDClassifier.predict` Open

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

NVIDIA/cuml#8361 · 1 comment · Opened Jul 9, 2026
Support sparse inputs to `LinearSVC`/`LinearSVR` Open

algo: svm

Difficulty 5/5 Over a week Newbie friendliness 30/100

NVIDIA/cuml#8335 · Opened Jul 6, 2026

Showing the newest 100

This page lists what was indexed most recently. Advanced filter has the whole inventory, narrowed by language, difficulty and how long a task takes.

Open advanced filter

NVIDIA/cuml

Showing the newest 100

Get new issues in your inbox