Cuml Versions Save

🚨 Breaking Changes

• Dropping Python 3.8 (#5385) @divyegala
• Support sparse input for SVC and SVR (#5273) @mfoerste4

🐛 Bug Fixes

• Fix for umap-pytest issue in Rocky8 and wheels in GHA nightly tests (#5458) @dantegd
• Fixes for nightly GHA runs (#5446) @dantegd
• Add missing RAFT cusolver_macros import and changes for recent cuDF updates (#5434) @dantegd
• Fix kmeans pytest to correctly compute fp output error (#5426) @mdoijade
• Add missing raft/matrix/matrix.cuh include (#5411) @benfred
• Fix path to cumlprims_mg in build workflow (#5406) @divyegala
• Fix path to cumlprims in build workflow (#5405) @vyasr
• Pin to scikit-build<17.2 (#5400) @vyasr
• Fix forward merge #5383 (#5384) @dantegd
• Correct buffer move assignment in experimental FIL (#5372) @wphicks
• Avoid invalid memory access in experimental FIL for large output size (#5365) @wphicks
• Fix forward merge #5336 (#5345) @dantegd

📖 Documentation

• Fix HDBSCAN docs and add membership_vector to cuml.cluster.hdbscan namespace (#5378) @beckernick
• Small doc fix (#5375) @tarang-jain

🚀 New Features

• Provide method for auto-optimization of FIL parameters (#5368) @wphicks

🛠️ Improvements

• Fix documentation source code links (#5449) @ajschmidt8
• Drop seaborn dependency. (#5437) @bdice
• Make all nvtx usage go through safe imports (#5424) @dantegd
• run docs nightly too (#5423) @AyodeAwe
• Switch back to using primary shared-action-workflows branch (#5420) @vyasr
• Add librmm to libcuml dependencies. (#5410) @bdice
• Update recipes to GTest version >=1.13.0 (#5408) @bdice
• Remove cudf from libcuml meta.yaml (#5407) @divyegala
• Support CUDA 12.0 for pip wheels (#5404) @divyegala
• Support for gtest 1.11+ changes (#5403) @dantegd
• Update cupy dependency (#5401) @vyasr
• Build wheels using new single image workflow (#5394) @vyasr
• Revert shared-action-workflows pin (#5391) @divyegala
• Fix logic for concatenating Treelite objects (#5387) @hcho3
• Dropping Python 3.8 (#5385) @divyegala
• Remove usage of rapids-get-rapids-version-from-git (#5379) @jjacobelli
• [ENH] Add missing includes of rmm/mr/device/per_device_resource.hpp (#5369) @ahendriksen
• Remove wheel pytest verbosity (#5367) @sevagh
• support parameter 'class_weight' and method 'decision_function' in LinearSVC (#5364) @mfoerste4
• Update clang-format to 16.0.1. (#5361) @bdice
• Implement apply() in FIL (#5358) @hcho3
• Use ARC V2 self-hosted runners for GPU jobs (#5356) @jjacobelli
• Try running silhouette test (#5353) @vyasr
• Remove uses-setup-env-vars (#5344) @vyasr
• Resolve auto-merger conflicts between branch-23.04 & branch-23.06 (#5340) @galipremsagar
• Solve merge conflict of PR #5327 (#5329) @dantegd
• Branch 23.06 merge 23.04 (#5315) @vyasr
• Support sparse input for SVC and SVR (#5273) @mfoerste4
• Delete outdated versions.json. (#5229) @bdice

🔗 Links

• Development Branch
• Compare with main branch

🚨 Breaking Changes

• Stop using setup.py in build.sh (#5500) @vyasr

🐛 Bug Fixes

• Fix test_masked_column_mode (#5480) @viclafargue
• Use fit_predict rather than fit for KNeighborsClassifier and KNeighborsRegressor in benchmark utility (#5460) @beckernick
• Modify HDBSCAN membership_vector batch_size check (#5455) @tarang-jain

🚀 New Features

• Use rapids-cmake testing to run tests in parallel (#5487) @robertmaynard
• cuml: Build CUDA 12 packages (#5318) @vyasr
• CI: Add custom GitHub Actions job to run clang-tidy (#5235) @csadorf

🛠️ Improvements

• Fixed potential overflows in SVM, minor adjustments to nvtx ranges (#5504) @mfoerste4
• Stop using setup.py in build.sh (#5500) @vyasr
• Fix PCA test (#5498) @viclafargue
• Update build dependencies (#5496) @csadorf
• Fix typos. (#5481) @bdice
• Add missing stream argument to cub calls in workingset (#5476) @mfoerste4
• Update to CMake 3.26.4 (#5464) @vyasr
• use rapids-upload-docs script (#5457) @AyodeAwe
• Unpin dask and distributed for development (#5452) @galipremsagar
• Remove documentation build scripts for Jenkins (#5450) @ajschmidt8
• Fix update version and pinnings for 23.08. (#5440) @bdice
• Add cython-lint configuration. (#5439) @bdice
• Unpin scikit-build upper bound (#5438) @vyasr
• Fix some deprecation warnings in tests. (#5436) @bdice
• Update raft::sparse::distance::pairwise_distance to new API (#5428) @divyegala

🚨 Breaking Changes

• Pin dask and distributed for release (#5333) @galipremsagar

🐛 Bug Fixes

• Skip pickle notebook during nbsphinx (#5342) @dantegd
• Avoid race condition in FIL predict_per_tree (#5334) @wphicks
• Ensure experimental FIL shmem usage is below device limits (#5326) @wphicks
• Update cuda architectures for threads per sm restriction (#5323) @wphicks
• Run experimental FIL tests in CI (#5316) @wphicks
• Run memory leak pytests without parallelism to avoid sporadic test failures (#5313) @dantegd
• Update cupy version for pip wheels (#5311) @dantegd
• Fix for raising attributeerors erroneously for ipython methods (#5299) @dantegd
• Fix cuml local cpp docs build (#5297) @galipremsagar
• Don't run dask tests twice when testing wheels (#5279) @benfred
• Remove MANIFEST.in use auto-generated one for sdists and package_data for wheels (#5278) @vyasr
• Removing remaining include of raft/distance/distance_type.hpp (#5264) @cjnolet
• Enable hypothesis testing for nightly test runs. (#5244) @csadorf
• Support numeric, boolean, and string keyword arguments to class methods during CPU dispatching (#5236) @beckernick
• Allowing large data in kmeans (#5228) @cjnolet

📖 Documentation

• Fix docs build to be pydata-sphinx-theme=0.13.0 compatible (#5259) @galipremsagar
• Add supported CPU/GPU operators to API docs and update docstrings (#5239) @beckernick
• Fix documentation author (#5126) @bdice

🚀 New Features

• Modify default batch size in HDBSCAN soft clustering (#5335) @tarang-jain
• reduce memory pressure in membership vector computation (#5268) @tarang-jain
• membership_vector for HDBSCAN (#5247) @tarang-jain
• Provide FIL implementation for both CPU and GPU (#4890) @wphicks

🛠️ Improvements

• Remove deprecated Treelite CI API from FIL (#5348) @hcho3
• Updated forest inference to new dask worker api for 23.04 (#5347) @taureandyernv
• Pin dask and distributed for release (#5333) @galipremsagar
• Pin cupy in wheel tests to supported versions (#5312) @vyasr
• Drop pickle5 (#5310) @jakirkham
• Remove CUDA_CHECK macro (#5308) @hcho3
• Revert faiss removal pinned tag (#5306) @cjnolet
• Upgrade to Treelite 3.2.0 (#5304) @hcho3
• Implement predict_per_tree() in FIL (#5303) @hcho3
• remove faiss from cuml (#5293) @benfred
• Stop setting package version attribute in wheels (#5285) @vyasr
• Add libfaiss runtime dependency to libcuml. (#5284) @bdice
• Move faiss_mr from raft (#5281) @benfred
• Generate pyproject dependencies with dfg (#5275) @vyasr
• Updating cuML to use consolidated RAFT libs (#5272) @cjnolet
• Add codespell as a linter (#5265) @benfred
• Pass AWS_SESSION_TOKEN and SCCACHE_S3_USE_SSL vars to conda build (#5263) @ajschmidt8
• Update to GCC 11 (#5258) @bdice
• Drop Python 3.7 handling for pickle protocol 4 (#5256) @jakirkham
• Migrate as much as possible to pyproject.toml (#5251) @vyasr
• Adapt to rapidsai/rmm#1221 which moves allocator callbacks (#5249) @wence-
• Add dfg as a pre-commit hook. (#5246) @vyasr
• Stop using versioneer to manage versions (#5245) @vyasr
• Enhance cuML benchmark utility and refactor hdbscan import utilities (#5242) @beckernick
• Fix GHA build workflow (#5241) @AjayThorve
• Support innerproduct distance in the pairwise_distance API (#5230) @benfred
• Enable hypothesis for 23.04 (#5221) @csadorf
• Reduce error handling verbosity in CI tests scripts (#5219) @AjayThorve
• Bump pinned pip wheel deps to 23.4 (#5217) @sevagh
• Update shared workflow branches (#5215) @ajschmidt8
• Unpin dask and distributed for development (#5209) @galipremsagar
• Remove gpuCI scripts. (#5208) @bdice
• Move date to build string in conda recipe (#5190) @ajschmidt8
• Kernel shap improvements (#5187) @vinaydes
• test out the raft bfknn replacement (#5186) @benfred
• Forward merge 23.02 into 23.04 (#5182) @vyasr
• Add detail namespace for linear models (#5107) @lowener
• Add pre-commit configuration (#4983) @csadorf

🔗 Links

• Development Branch
• Compare with main branch

🐛 Bug Fixes

• Skipping some hdbscan tests when cuda version is <= 11.2. (#4916) @cjnolet
• Fix HDBSCAN python namespace (#4895) @cjnolet
• Cupy 11 fixes (#4889) @dantegd
• Fix small fp precision failure in linear regression doctest test (#4884) @lowener
• Remove unused cuDF imports (#4873) @beckernick
• Update for thrust 1.17 and fixes to accommodate for cuDF Buffer refactor (#4871) @dantegd
• Use rapids-cmake 22.10 best practice for RAPIDS.cmake location (#4862) @robertmaynard
• Patch for nightly test&bench (#4840) @viclafargue
• Fixed Large memory requirements for SimpleImputer strategy median #4794 (#4817) @erikrene
• Transforms RandomForest estimators non-consecutive labels to consecutive labels where appropriate (#4780) @VamsiTallam95

📖 Documentation

• Document that minimum required CMake version is now 3.23.1 (#4899) @robertmaynard
• Update KMeans notebook for clarity (#4886) @beckernick

🚀 New Features

• Allow cupy 11 (#4880) @galipremsagar
• Add sample_weight to Coordinate Descent solver (Lasso and ElasticNet) (#4867) @lowener
• Import treelite models into FIL in a different precision (#4839) @canonizer
• #4783 Added nan_euclidean distance metric to pairwise_distances (#4797) @SreekiranprasadV
• PowerTransformer, QuantileTransformer and KernelCenterer (#4755) @viclafargue
• Add "median" to TargetEncoder (#4722) @daxiongshu
• New Feature StratifiedKFold (#3109) @daxiongshu

🛠️ Improvements

• Update cuda-python dependency to 11.7.1 (#4948) @shwina
• Updating python to use pylibraft (#4887) @cjnolet
• Upgrade Treelite to 3.0.0 (#4885) @hcho3
• Statically link all CUDA toolkit libraries (#4881) @trxcllnt
• approximate_predict function for HDBSCAN (#4872) @tarang-jain
• Pin dask and distributed for release (#4859) @galipremsagar
• Remove Raft deprecated headers (#4858) @lowener
• Fix forward-merge conflicts (#4857) @ajschmidt8
• Update the NVTX bench helper for the new nsys utility (#4826) @viclafargue
• All points membership vector for HDBSCAN (#4800) @tarang-jain
• TSNE and UMAP allow several distance types (#4779) @tarang-jain
• Convert fp32 datasets to fp64 in ARIMA and AutoARIMA + update notebook to avoid deprecation warnings with positional parameters (#4195) @Nyrio

🔗 Links

• Development Branch
• Compare with main branch

🚨 Breaking Changes

• Use ivf_pq and ivf_flat from raft (#5119) @benfred
• Estimators adaptation toward CPU/GPU interoperability (#4918) @viclafargue
• Provide host CumlArray and associated infrastructure (#4908) @wphicks
• Improvements of UMAP/TSNE precomputed KNN feature (#4865) @viclafargue

🐛 Bug Fixes

• Fix for creation of CUDA context at import time (#5211) @dantegd
• Correct arguments to load_from_treelite_model after classmethod conversion (#5210) @wphicks
• Use workaround to avoid staticmethod 3.10/Cython issue (#5202) @wphicks
• Increase margin for flaky FIL test (#5194) @wphicks
• Increase margin for flaky FIL test (#5174) @wphicks
• Fix gather_if raft update (#5149) @lowener
• Add _predict_model_on_cpu for RandomForestClassifier (#5148) @lowener
• Fix for hdbscan model serialization (#5128) @cjnolet
• build.sh switch to use RAPIDS magic value (#5124) @robertmaynard
• Fix Lasso interop issue (#5116) @viclafargue
• Remove nvcc conda package and add compiler/ninja to dev envs (#5113) @dantegd
• Add missing job dependency for new PR jobs check (#5112) @dantegd
• Skip RAFT docstring test in cuML (#5088) @dantegd
• Restore KNN metric attribute (#5087) @viclafargue
• Check sklearn presence before importing the Pipeline (#5072) @viclafargue
• Provide workaround for kernel ridge solver (#5064) @wphicks
• Keep verbosity level in KMeans OPG (#5063) @viclafargue
• Transmit verbosity level to Dask workers (#5062) @viclafargue
• Ensure consistent order for nearest neighbor tests (#5059) @wphicks
• Add workers argument to dask make_blobs (#5057) @viclafargue
• Fix indexing type for ridge and linear models (#4996) @lowener

📖 Documentation

• Adding benchmark notebook for hdbscan soft clustering (#5103) @cjnolet
• Fix doc for solver in LogisticRegression (#5097) @viclafargue
• Fix docstring of HashingVectorizer (#5041) @lowener
• expose text, text.{CountVectorizer,HashingVectorizer,Tfidf{Transformer,Vectorizer}} from feature_extraction's public api (#5028) @mattf
• Add Dask LabelEncoder to the documentation (#5023) @beckernick

🚀 New Features

• HDBSCAN CPU/GPU Interop (#5137) @divyegala
• Make all CPU/GPU only imports "safe" for respective package (#5117) @wphicks
• Pickling for HBDSCAN (#5102) @divyegala
• Break up silhouette score into 3 units to improve compilation time (#5061) @wphicks
• Provide host CumlArray and associated infrastructure (#4908) @wphicks

🛠️ Improvements

• Pin dask and distributed for release (#5198) @galipremsagar
• Update shared workflow branches (#5197) @ajschmidt8
• Pin wheel dependencies to same RAPIDS release (#5183) @sevagh
• Reverting RAFT pin (#5178) @cjnolet
• Remove faiss from libcuml (#5175) @ajschmidt8
• Update location of import_utils from common to internals for Forest notebook (#5171) @taureandyernv
• Disable hypothesis tests for 23.02 burndown. (#5168) @csadorf
• Use CTK 118/cp310 branch of wheel workflows (#5163) @sevagh
• Add docs build GH (#5155) @AjayThorve
• Adapt to changes in cudf.core.buffer.Buffer (#5154) @galipremsagar
• Upgrade Treelite to 3.1.0 (#5146) @hcho3
• Replace cpdef variables with cdef variables. (#5145) @bdice
• Update Scikit-learn compatibility to 1.2 (#5141) @dantegd
• Replace deprecated raft headers (#5134) @lowener
• Execution device interoperability documentation (#5130) @viclafargue
• Remove outdated macOS deployment target from build script. (#5125) @bdice
• Build CUDA 11.8 and Python 3.10 Packages (#5120) @bdice
• Use ivf_pq and ivf_flat from raft (#5119) @benfred
• Update workflows for nightly tests (#5110) @ajschmidt8
• Build pip wheels alongside conda CI (#5109) @sevagh
• Remove PROJECT_FLASH from libcuml conda build environment. (#5108) @bdice
• Enable Recently Updated Check (#5105) @ajschmidt8
• Ensure pytest is run from relevant directories in GH Actions (#5101) @ajschmidt8
• Remove C++ Kmeans test (#5098) @lowener
• Slightly lower the test_mbsgd_regressor expected min score. (#5092) @csadorf
• Skip all hypothesis health checks by default in CI runs. (#5090) @csadorf
• Reduce Naive Bayes test time (#5082) @lowener
• Remove unused .conda folder (#5078) @ajschmidt8
• Fix conflicts in #5045 (#5077) @ajschmidt8
• Add GitHub Actions Workflows (#5075) @csadorf
• Skip test_linear_regression_model_default test. (#5074) @csadorf
• Fix link. (#5067) @bdice
• Expand hypothesis testing for linear models (#5065) @csadorf
• Update xgb version in GPU CI 23.02 to 1.7.1 and unblocking CI (#5051) @dantegd
• Remove direct UCX and NCCL dependencies (#5038) @vyasr
• Move single test from test to tests (#5037) @vyasr
• Support using CountVectorizer & TfidVectorizer in cuml.pipeline.Pipeline (#5034) @lasse-it
• Refactor API decorators (#5026) @csadorf
• Implement hypothesis strategies and tests for arrays (#5017) @csadorf
• Add dependencies.yaml for rapids-dependency-file-generator (#5003) @beckernick
• Improved CPU/GPU interoperability (#5001) @viclafargue
• Estimators adaptation toward CPU/GPU interoperability (#4918) @viclafargue
• Improvements of UMAP/TSNE precomputed KNN feature (#4865) @viclafargue

🚨 Breaking Changes

• Use ivf_pq and ivf_flat from raft (#5119) @benfred
• Estimators adaptation toward CPU/GPU interoperability (#4918) @viclafargue
• Provide host CumlArray and associated infrastructure (#4908) @wphicks
• Improvements of UMAP/TSNE precomputed KNN feature (#4865) @viclafargue

🐛 Bug Fixes

• Fix for creation of CUDA context at import time (#5211) @dantegd
• Correct arguments to load_from_treelite_model after classmethod conversion (#5210) @wphicks
• Use workaround to avoid staticmethod 3.10/Cython issue (#5202) @wphicks
• Increase margin for flaky FIL test (#5194) @wphicks
• Increase margin for flaky FIL test (#5174) @wphicks
• Fix gather_if raft update (#5149) @lowener
• Add _predict_model_on_cpu for RandomForestClassifier (#5148) @lowener
• Fix for hdbscan model serialization (#5128) @cjnolet
• build.sh switch to use RAPIDS magic value (#5124) @robertmaynard
• Fix Lasso interop issue (#5116) @viclafargue
• Remove nvcc conda package and add compiler/ninja to dev envs (#5113) @dantegd
• Add missing job dependency for new PR jobs check (#5112) @dantegd
• Skip RAFT docstring test in cuML (#5088) @dantegd
• Restore KNN metric attribute (#5087) @viclafargue
• Check sklearn presence before importing the Pipeline (#5072) @viclafargue
• Provide workaround for kernel ridge solver (#5064) @wphicks
• Keep verbosity level in KMeans OPG (#5063) @viclafargue
• Transmit verbosity level to Dask workers (#5062) @viclafargue
• Ensure consistent order for nearest neighbor tests (#5059) @wphicks
• Add workers argument to dask make_blobs (#5057) @viclafargue
• Fix indexing type for ridge and linear models (#4996) @lowener

📖 Documentation

• Adding benchmark notebook for hdbscan soft clustering (#5103) @cjnolet
• Fix doc for solver in LogisticRegression (#5097) @viclafargue
• Fix docstring of HashingVectorizer (#5041) @lowener
• expose text, text.{CountVectorizer,HashingVectorizer,Tfidf{Transformer,Vectorizer}} from feature_extraction's public api (#5028) @mattf
• Add Dask LabelEncoder to the documentation (#5023) @beckernick

🚀 New Features

• HDBSCAN CPU/GPU Interop (#5137) @divyegala
• Make all CPU/GPU only imports "safe" for respective package (#5117) @wphicks
• Pickling for HBDSCAN (#5102) @divyegala
• Break up silhouette score into 3 units to improve compilation time (#5061) @wphicks
• Provide host CumlArray and associated infrastructure (#4908) @wphicks

🛠️ Improvements

• Pin dask and distributed for release (#5198) @galipremsagar
• Update shared workflow branches (#5197) @ajschmidt8
• Pin wheel dependencies to same RAPIDS release (#5183) @sevagh
• Reverting RAFT pin (#5178) @cjnolet
• Remove faiss from libcuml (#5175) @ajschmidt8
• Update location of import_utils from common to internals for Forest notebook (#5171) @taureandyernv
• Disable hypothesis tests for 23.02 burndown. (#5168) @csadorf
• Use CTK 118/cp310 branch of wheel workflows (#5163) @sevagh
• Add docs build GH (#5155) @AjayThorve
• Adapt to changes in cudf.core.buffer.Buffer (#5154) @galipremsagar
• Upgrade Treelite to 3.1.0 (#5146) @hcho3
• Replace cpdef variables with cdef variables. (#5145) @bdice
• Update Scikit-learn compatibility to 1.2 (#5141) @dantegd
• Replace deprecated raft headers (#5134) @lowener
• Execution device interoperability documentation (#5130) @viclafargue
• Remove outdated macOS deployment target from build script. (#5125) @bdice
• Build CUDA 11.8 and Python 3.10 Packages (#5120) @bdice
• Use ivf_pq and ivf_flat from raft (#5119) @benfred
• Update workflows for nightly tests (#5110) @ajschmidt8
• Build pip wheels alongside conda CI (#5109) @sevagh
• Remove PROJECT_FLASH from libcuml conda build environment. (#5108) @bdice
• Enable Recently Updated Check (#5105) @ajschmidt8
• Ensure pytest is run from relevant directories in GH Actions (#5101) @ajschmidt8
• Remove C++ Kmeans test (#5098) @lowener
• Slightly lower the test_mbsgd_regressor expected min score. (#5092) @csadorf
• Skip all hypothesis health checks by default in CI runs. (#5090) @csadorf
• Reduce Naive Bayes test time (#5082) @lowener
• Remove unused .conda folder (#5078) @ajschmidt8
• Fix conflicts in #5045 (#5077) @ajschmidt8
• Add GitHub Actions Workflows (#5075) @csadorf
• Skip test_linear_regression_model_default test. (#5074) @csadorf
• Fix link. (#5067) @bdice
• Expand hypothesis testing for linear models (#5065) @csadorf
• Update xgb version in GPU CI 23.02 to 1.7.1 and unblocking CI (#5051) @dantegd
• Remove direct UCX and NCCL dependencies (#5038) @vyasr
• Move single test from test to tests (#5037) @vyasr
• Support using CountVectorizer & TfidVectorizer in cuml.pipeline.Pipeline (#5034) @lasse-it
• Refactor API decorators (#5026) @csadorf
• Implement hypothesis strategies and tests for arrays (#5017) @csadorf
• Add dependencies.yaml for rapids-dependency-file-generator (#5003) @beckernick
• Improved CPU/GPU interoperability (#5001) @viclafargue
• Estimators adaptation toward CPU/GPU interoperability (#4918) @viclafargue
• Improvements of UMAP/TSNE precomputed KNN feature (#4865) @viclafargue

🔗 Links

• Development Branch
• Compare with main branch

🐛 Bug Fixes

• Don't run dask tests twice when testing wheels (#5279) @benfred
• Remove MANIFEST.in use auto-generated one for sdists and package_data for wheels (#5278) @vyasr
• Removing remaining include of raft/distance/distance_type.hpp (#5264) @cjnolet
• Enable hypothesis testing for nightly test runs. (#5244) @csadorf
• Allowing large data in kmeans (#5228) @cjnolet

📖 Documentation

• Fix docs build to be pydata-sphinx-theme=0.13.0 compatible (#5259) @galipremsagar
• Add supported CPU/GPU operators to API docs and update docstrings (#5239) @beckernick

🛠️ Improvements

• Move faiss_mr from raft (#5281) @benfred
• Add codespell as a linter (#5265) @benfred
• Pass AWS_SESSION_TOKEN and SCCACHE_S3_USE_SSL vars to conda build (#5263) @ajschmidt8
• Update to GCC 11 (#5258) @bdice
• Drop Python 3.7 handling for pickle protocol 4 (#5256) @jakirkham
• Migrate as much as possible to pyproject.toml (#5251) @vyasr
• Adapt to rapidsai/rmm#1221 which moves allocator callbacks (#5249) @wence-
• Add dfg as a pre-commit hook. (#5246) @vyasr
• Stop using versioneer to manage versions (#5245) @vyasr
• Enhance cuML benchmark utility and refactor hdbscan import utilities (#5242) @beckernick
• Fix GHA build workflow (#5241) @AjayThorve
• Support innerproduct distance in the pairwise_distance API (#5230) @benfred
• Enable hypothesis for 23.04 (#5221) @csadorf
• Reduce error handling verbosity in CI tests scripts (#5219) @AjayThorve
• Bump pinned pip wheel deps to 23.4 (#5217) @sevagh
• Update shared workflow branches (#5215) @ajschmidt8
• Unpin dask and distributed for development (#5209) @galipremsagar
• Remove gpuCI scripts. (#5208) @bdice
• Move date to build string in conda recipe (#5190) @ajschmidt8
• Kernel shap improvements (#5187) @vinaydes
• test out the raft bfknn replacement (#5186) @benfred
• Forward merge 23.02 into 23.04 (#5182) @vyasr
• Add pre-commit configuration (#4983) @csadorf

🔗 Links

• Development Branch
• Compare with main branch

🚨 Breaking Changes

• Change docs theme to pydata-sphinx theme (#4985) @galipremsagar
• Remove "Open In Colab" link from Estimator Intro notebook. (#4980) @bdice
• Remove CumlArray.copy() (#4958) @madsbk

🐛 Bug Fixes

• Backport "Don't initialize CUDA context if RAPIDS_NO_INITIALIZE env variable is set" (#5069) @dantegd
• Remove cupy.cusparse custom serialization (#5024) @dantegd
• Restore LinearRegression documentation (#5020) @viclafargue
• Don't use CMake 3.25.0 as it has a FindCUDAToolkit show stopping bug (#5007) @robertmaynard
• verifying cusparse wrapper revert passes CI (#4990) @cjnolet
• Use rapdsi_cpm_find(COMPONENTS ) for proper component tracking (#4989) @robertmaynard
• Fix integer overflow in AutoARIMA due to bool-to-int cub scan (#4971) @Nyrio
• Add missing includes (#4947) @vyasr
• Fix the CMake option for disabling deprecation warnings. (#4946) @vyasr
• Make doctest resilient to changes in cupy reprs (#4945) @vyasr
• Assign python/ sub-directory to python-codeowners (#4940) @csadorf
• Fix for non-contiguous strides (#4736) @viclafargue

📖 Documentation

• Change docs theme to pydata-sphinx theme (#4985) @galipremsagar
• Remove "Open In Colab" link from Estimator Intro notebook. (#4980) @bdice
• Updating build instructions (#4979) @cjnolet

🚀 New Features

• Reenable copy_prs. (#5010) @vyasr
• Add wheel builds (#5009) @vyasr
• LinearRegression: add support for multiple targets (#4988) @ahendriksen
• CPU/GPU interoperability POC (#4874) @viclafargue

🛠️ Improvements

• Upgrade Treelite to 3.0.1 (#5018) @hcho3
• fix addition of nan_euclidean_distances to public api (#5015) @mattf
• Fixing raft pin to 22.12 (#5000) @cjnolet
• Pin dask and distributed for release (#4999) @galipremsagar
• Update dask nightly install command in CI (#4978) @galipremsagar
• Improve error message for array_equal asserts. (#4973) @csadorf
• Use new rapids-cmake functionality for rpath handling. (#4966) @vyasr
• Impl. CumlArray.deserialize() (#4965) @madsbk
• Update cuda-python dependency to 11.7.1 (#4961) @galipremsagar
• Add check for nsys utility version in the nvtx_benchmarks.py script (#4959) @viclafargue
• Remove CumlArray.copy() (#4958) @madsbk
• Implement hypothesis-based tests for linear models (#4952) @csadorf
• Switch to using rapids-cmake for gbench. (#4950) @vyasr
• Remove stale labeler (#4949) @raydouglass
• Fix url in python/setup.py setuptools metadata. (#4937) @csadorf
• Updates to fix cuml build (#4928) @cjnolet
• Documenting hdbscan module to add prediction functions (#4925) @cjnolet
• Unpin dask and distributed for development (#4912) @galipremsagar
• Use KMeans from Raft (#4713) @lowener
• Update cuml raft header extensions (#4599) @cjnolet
• Reconciling primitives moved to RAFT (#4583) @cjnolet

🚨 Breaking Changes

• Change docs theme to pydata-sphinx theme (#4985) @galipremsagar
• Remove "Open In Colab" link from Estimator Intro notebook. (#4980) @bdice
• Remove CumlArray.copy() (#4958) @madsbk

🐛 Bug Fixes

• Remove cupy.cusparse custom serialization (#5024) @dantegd
• Restore LinearRegression documentation (#5020) @viclafargue
• Don't use CMake 3.25.0 as it has a FindCUDAToolkit show stopping bug (#5007) @robertmaynard
• verifying cusparse wrapper revert passes CI (#4990) @cjnolet
• Use rapdsi_cpm_find(COMPONENTS ) for proper component tracking (#4989) @robertmaynard
• Fix integer overflow in AutoARIMA due to bool-to-int cub scan (#4971) @Nyrio
• Add missing includes (#4947) @vyasr
• Fix the CMake option for disabling deprecation warnings. (#4946) @vyasr
• Make doctest resilient to changes in cupy reprs (#4945) @vyasr
• Assign python/ sub-directory to python-codeowners (#4940) @csadorf
• Fix for non-contiguous strides (#4736) @viclafargue

📖 Documentation

• Change docs theme to pydata-sphinx theme (#4985) @galipremsagar
• Remove "Open In Colab" link from Estimator Intro notebook. (#4980) @bdice
• Updating build instructions (#4979) @cjnolet

🚀 New Features

• Reenable copy_prs. (#5010) @vyasr
• Add wheel builds (#5009) @vyasr
• LinearRegression: add support for multiple targets (#4988) @ahendriksen
• CPU/GPU interoperability POC (#4874) @viclafargue

🛠️ Improvements

• Upgrade Treelite to 3.0.1 (#5018) @hcho3
• fix addition of nan_euclidean_distances to public api (#5015) @mattf
• Fixing raft pin to 22.12 (#5000) @cjnolet
• Pin dask and distributed for release (#4999) @galipremsagar
• Update dask nightly install command in CI (#4978) @galipremsagar
• Improve error message for array_equal asserts. (#4973) @csadorf
• Use new rapids-cmake functionality for rpath handling. (#4966) @vyasr
• Impl. CumlArray.deserialize() (#4965) @madsbk
• Update cuda-python dependency to 11.7.1 (#4961) @galipremsagar
• Add check for nsys utility version in the nvtx_benchmarks.py script (#4959) @viclafargue
• Remove CumlArray.copy() (#4958) @madsbk
• Implement hypothesis-based tests for linear models (#4952) @csadorf
• Switch to using rapids-cmake for gbench. (#4950) @vyasr
• Remove stale labeler (#4949) @raydouglass
• Fix url in python/setup.py setuptools metadata. (#4937) @csadorf
• Updates to fix cuml build (#4928) @cjnolet
• Documenting hdbscan module to add prediction functions (#4925) @cjnolet
• Unpin dask and distributed for development (#4912) @galipremsagar
• Use KMeans from Raft (#4713) @lowener
• Update cuml raft header extensions (#4599) @cjnolet
• Reconciling primitives moved to RAFT (#4583) @cjnolet

🐛 Bug Fixes

• Skipping some hdbscan tests when cuda version is <= 11.2. (#4916) @cjnolet
• Fix HDBSCAN python namespace (#4895) @cjnolet
• Cupy 11 fixes (#4889) @dantegd
• Fix small fp precision failure in linear regression doctest test (#4884) @lowener
• Remove unused cuDF imports (#4873) @beckernick
• Update for thrust 1.17 and fixes to accommodate for cuDF Buffer refactor (#4871) @dantegd
• Use rapids-cmake 22.10 best practice for RAPIDS.cmake location (#4862) @robertmaynard
• Patch for nightly test&bench (#4840) @viclafargue
• Fixed Large memory requirements for SimpleImputer strategy median #4794 (#4817) @erikrene
• Transforms RandomForest estimators non-consecutive labels to consecutive labels where appropriate (#4780) @VamsiTallam95

📖 Documentation

• Document that minimum required CMake version is now 3.23.1 (#4899) @robertmaynard
• Update KMeans notebook for clarity (#4886) @beckernick

🚀 New Features

• Allow cupy 11 (#4880) @galipremsagar
• Add sample_weight to Coordinate Descent solver (Lasso and ElasticNet) (#4867) @lowener
• Import treelite models into FIL in a different precision (#4839) @canonizer
• #4783 Added nan_euclidean distance metric to pairwise_distances (#4797) @Sreekiran096
• PowerTransformer, QuantileTransformer and KernelCenterer (#4755) @viclafargue
• Add "median" to TargetEncoder (#4722) @daxiongshu
• New Feature StratifiedKFold (#3109) @daxiongshu

🛠️ Improvements

• Update cuda-python dependency to 11.7.1 (#4948) @shwina
• Updating python to use pylibraft (#4887) @cjnolet
• Upgrade Treelite to 3.0.0 (#4885) @hcho3
• Statically link all CUDA toolkit libraries (#4881) @trxcllnt
• approximate_predict function for HDBSCAN (#4872) @tarang-jain
• Pin dask and distributed for release (#4859) @galipremsagar
• Remove Raft deprecated headers (#4858) @lowener
• Fix forward-merge conflicts (#4857) @ajschmidt8
• Update the NVTX bench helper for the new nsys utility (#4826) @viclafargue
• All points membership vector for HDBSCAN (#4800) @tarang-jain
• TSNE and UMAP allow several distance types (#4779) @tarang-jain
• Convert fp32 datasets to fp64 in ARIMA and AutoARIMA + update notebook to avoid deprecation warnings with positional parameters (#4195) @Nyrio