1.7.1

Fixes

• Set a lower bound for mlflow in mlserver-mlflow by @crispin-ki in #2114
• Set lower bounds for protobuf, grpcio, and grpcio-tools by @RobertSamoilescu in #2175
• Added support for bytes encoding in PandasCodec by @RobertSamoilescu in #2117

What's Changed

• Included more docker labels by @RobertSamoilescu in #2106
• Fix too loose mlflow dependency constraint in mlserver-mlflow by @crispin-ki in #2114
• Fixed byte encoding in the PandasCodec by @RobertSamoilescu in #2117
• Update CHANGELOG by @github-actions in #2108
• Re-generate License Info by @github-actions in #2174
• Re-generate License Info by @github-actions in #2176
• Fix protobuf bounds by @RobertSamoilescu in #2175
• Revert "build(deps-dev): bump transformers from 4.41.2 to 4.52.4 (#2170)" by @RobertSamoilescu in #2177
• ci: Merge change for release 1.7.1 by @RobertSamoilescu in #2178
• Re-generate License Info by @github-actions in #2180
• ci: Merge change for release 1.7.1 [2] (#2180) by @RobertSamoilescu in #2182

New Contributors

• @crispin-ki made their first contribution in #2114

Full Changelog: 1.7.0...1.7.1

1.7.0

Overview

Features

• MLServer has now support for Python 3.11 and 3.12 by @shivakrishnaah in (#1951)
• MLServer now supports enabling assignment of models to dedicated inference pool groups to avoid risk of starvation by @RobertSamoilescu in (##2040)
• MLServer now includes compatibility with additional column types available in the MLflow runtime such as: Array, Map, Object, Any by @RobertSamoilescu in (#2080)

Fixes

• Relaxing Pydantic dependencies by @lemonhead94 in (#1928)
• Adjusted the version range for FastAPI to ensure compatibility with future releases by @sergioave in (#1954)
• Forward rest parameters to model @idlefella in (#1921)
• Force clean up env fix by @sakoush in (#2029)
• PandasCodec improperly encoding columns of numeric lists fix by @RobertSamoilescu in (#2080)
• Opentelemetry dependency mismatch fix by @lawrence-c in (#2088)
• AdaptiveBatcher timeout calculation fix by @hanlaur in (#2093)

What's Changed

• Update CHANGELOG by @github-actions in #1905
• docs: add docs for gitbook by @sakoush in #1919
• Relaxing Pydantic dependencies by @lemonhead94 in #1928
• build(deps): Upgrade fastapi and starlette by @sakoush in #1934
• Re-generate License Info by @github-actions in #1935
• Update FastAPI version constraint by @sergioave in #1954
• Forward rest parameters to model by @idlefella in #1921
• Revert "build(deps): bump mlflow from 2.18.0 to 2.19.0 in /runtimes/mlflow" by @sakoush in #1988
• Added dependency upgrades for python3.12 support by @shivakrishnaah in #1951
• Re-generate License Info by @github-actions in #1991
• Further CI fixes for py312 support by @sakoush in #1992
• Revert "build(deps): bump python-multipart from 0.0.9 to 0.0.18 in /runtimes/alibi-detect" by @sakoush in #1994
• Re-generate License Info by @github-actions in #2027
• Force clean up env (for py 3.12) by @sakoush in #2029
• Pinned preflight to latest version by @RobertSamoilescu in #2041
• Bump gevent to 24.11.1 by @RobertSamoilescu in #2042
• Bumped python-multipart to 0.0.20 by @RobertSamoilescu in #2043
• Bumped python-multipart-0.0.20 on alibi-explain runtime by @RobertSamoilescu in #2044
• Included separate inference pool by @RobertSamoilescu in #2040
• Wrote docs for inference_pool_gid by @RobertSamoilescu in #2045
• Update lightgbm in alibi runtime to 4.6 by @sakoush in #2081
• Fix pandas codec by @RobertSamoilescu in #2080
• Fix interceptors insert tuple -> list by @lawrence-c in #2088
• Fix AdaptiveBatcher timeout calculation by @hanlaur in #2093
• Fix onnxruntime version by @RobertSamoilescu in #2100
• Included labels for preflight checks by @RobertSamoilescu in #2101
• Bumped poetry to 2.1.1 by @RobertSamoilescu in #2103
• Add installation for poetry export plugin by @RobertSamoilescu in #2104
• ci: Merge change for release 1.7.0 [4] by @RobertSamoilescu in #2107

New Contributors

• @lemonhead94 made their first contribution in #1928
• @sergioave made their first contribution in #1954
• @shivakrishnaah made their first contribution in #1951
• @lawrence-c made their first contribution in #2088
• @hanlaur made their first contribution in #2093

Full Changelog: 1.6.1...1.7.0

1.6.1

Overview

Features

MLServer now offers an option to use pre-existing Python environments by specifying a path to the environment to be used - by @idlefella in (#1891)

Releases

MLServer released catboost runtime which allows serving catboost models with MLServer - by @sakoush in (#1839)

Fixes

• Kafka json byte encoding fix to match rest server by @DerTiedemann and @sakoush in (#1622)
• Prometheus interceptor fix for gRPC streaming by @RobertSamoilescu in (#1858)

What's Changed

• Re-generate License Info by @github-actions in #1812
• Update CHANGELOG by @github-actions in #1830
• Update release.yml to include catboost by @sakoush in #1839
• Fix kafka json byte encoding to match rest server by @DerTiedemann in #1622
• Included Prometheus interceptor support for gRPC streaming by @RobertSamoilescu in #1858
• Run gRPC test serially by @RobertSamoilescu in #1872
• Re-generate License Info by @github-actions in #1886
• Feature/support existing environments by @idlefella in #1891
• Fix tensorflow upperbound macos by @RobertSamoilescu in #1901
• ci: Merge change for release 1.6.1 by @RobertSamoilescu in #1902
• Bump preflight to 1.10.0 by @RobertSamoilescu in #1903
• ci: Merge change for release 1.6.1 [2] by @RobertSamoilescu in #1904

New Contributors

• @DerTiedemann made their first contribution in #1622
• @idlefella made their first contribution in #1891

Full Changelog: 1.6.0...1.6.1

1.6.0

Overview

Upgrades

MLServer supports Pydantic V2.

Features

MLServer supports streaming data to and from your models.

Streaming support is available for both the REST and gRPC servers:

• for the REST server is limited only to server streaming. This means that the client sends a single request to the server, and the server responds with a stream of data.
• for the gRPC server is available for both client and server streaming. This means that the client sends a stream of data to the server, and the server responds with a stream of data.

See our docs and example for more details.

What's Changed

• fix(ci): fix typo in CI name by @sakoush in #1623
• Update CHANGELOG by @github-actions in #1624
• Re-generate License Info by @github-actions in #1634
• Fix mlserver_huggingface settings device type by @geodavic in #1486
• fix: Adjust HF tests post-merge of PR #1486 by @sakoush in #1635
• Update README.md w licensing clarification by @paulb-seldon in #1636
• Re-generate License Info by @github-actions in #1642
• fix(ci): optimise disk space for GH workers by @sakoush in #1644
• build: Update maintainers by @jesse-c in #1659
• fix: Missing f-string directives by @jesse-c in #1677
• build: Add Catboost runtime to Dependabot by @jesse-c in #1689
• Fix JSON input shapes by @ReveStobinson in #1679
• build(deps): bump alibi-detect from 0.11.5 to 0.12.0 by @jesse-c in #1702
• build(deps): bump alibi from 0.9.5 to 0.9.6 by @jesse-c in #1704
• Docs correction - Updated README.md in mlflow to match column names order by @vivekk0903 in #1703
• fix(runtimes): Remove unused Pydantic dependencies by @jesse-c in #1725
• test: Detect generate failures by @jesse-c in #1729
• build: Add granularity in types generation by @jesse-c in #1749
• Migrate to Pydantic v2 by @jesse-c in #1748
• Re-generate License Info by @github-actions in #1753
• Revert "build(deps): bump uvicorn from 0.28.0 to 0.29.0" by @jesse-c in #1758
• refactor(pydantic): Remaining migrations for deprecated functions by @jesse-c in #1757
• Fixed openapi dataplane.yaml by @RobertSamoilescu in #1752
• fix(pandas): Use Pydantic v2 compatible type by @jesse-c in #1760
• Fix Pandas codec decoding from numpy arrays by @lhnwrk in #1751
• build: Bump versions for Read the Docs by @jesse-c in #1761
• docs: Remove quotes around local TOC by @jesse-c in #1764
• Spawn worker in custom environment by @lhnwrk in #1739
• Re-generate License Info by @github-actions in #1767
• basic contributing guide on contributing and opening a PR by @bohemia420 in #1773
• Inference streaming support by @RobertSamoilescu in #1750
• Re-generate License Info by @github-actions in #1779
• build: Lock GitHub runners' OS by @jesse-c in #1765
• Removed text-model form benchmarking by @RobertSamoilescu in #1790
• Bumped mlflow to 2.13.1 and gunicorn to 22.0.0 by @RobertSamoilescu in #1791
• Build(deps): Update to poetry version 1.8.3 in docker build by @sakoush in #1792
• Bumped werkzeug to 3.0.3 by @RobertSamoilescu in #1793
• Docs streaming by @RobertSamoilescu in #1789
• Bump uvicorn 0.30.1 by @RobertSamoilescu in #1795
• Fixes for all-runtimes by @RobertSamoilescu in #1794
• Fix BaseSettings import for pydantic v2 by @RobertSamoilescu in #1798
• Bumped preflight version to 1.9.7 by @RobertSamoilescu in #1797
• build: Install dependencies only in Tox environments by @jesse-c in #1785
• Bumped to 1.6.0.dev2 by @RobertSamoilescu in #1803
• Fix CI/CD macos-huggingface by @RobertSamoilescu in #1805
• Fixed macos kafka CI by @RobertSamoilescu in #1807
• Update poetry lock by @RobertSamoilescu in #1808
• Re-generate License Info by @github-actions in #1813
• Fix/macos all runtimes by @RobertSamoilescu in #1823
• fix: Update stale reviewer in licenses.yml workflow by @sakoush in #1824
• ci: Merge changes from master to release branch by @sakoush in #1825

New Contributors

• @paulb-seldon made their first contribution in #1636
• @ReveStobinson made their first contribution in #1679
• @vivekk0903 made their first contribution in #1703
• @RobertSamoilescu made their first contribution in #1752
• @lhnwrk made their first contribution in #1751
• @bohemia420 made their first contribution in #1773

Full Changelog: 1.5.0...1.6.0

1.5.0

What's Changed

• Update CHANGELOG by @github-actions in #1592
• build: Migrate away from Node v16 actions by @jesse-c in #1596
• build: Bump version and improve release doc by @jesse-c in #1602
• build: Upgrade stale packages (fastapi, starlette, tensorflow, torch) by @sakoush in #1603
• fix(ci): tests and security workflow fixes by @sakoush in #1608
• Re-generate License Info by @github-actions in #1612
• fix(ci): Missing quote in CI test for all_runtimes by @sakoush in #1617
• build(docker): Bump dependencies by @jesse-c in #1618
• docs: List supported Python versions by @jesse-c in #1591
• fix(ci): Have separate smaller tasks for release by @sakoush in #1619

Notes

• We remove support for python 3.8, check #1603 for more info. Docker images for mlserver are already using python 3.10.

Full Changelog: 1.4.0...1.5.0

1.4.0

What's Changed

• Free up some space for GH actions by @adriangonz in #1282
• Introduce tracing with OpenTelemetry by @vtaskow in #1281
• Update release CI to use Poetry by @adriangonz in #1283
• Re-generate License Info by @github-actions in #1284
• Add support for white-box explainers to alibi-explain runtime by @ascillitoe in #1279
• Update CHANGELOG by @github-actions in #1294
• Fix build-wheels.sh error when copying to output path by @lc525 in #1286
• Fix typo by @strickvl in #1289
• feat(logging): Distinguish logs from different models by @vtaskow in #1302
• Make sure we use our Response class by @adriangonz in #1314
• Adding Quick-Start Guide to docs by @ramonpzg in #1315
• feat(logging): Provide JSON-formatted structured logging as option by @vtaskow in #1308
• Bump in conda version and mamba solver by @dtpryce in #1298
• feat(huggingface): Merge model settings by @jesse-c in #1337
• feat(huggingface): Load local artefacts in HuggingFace runtime by @vtaskow in #1319
• Document and test behaviour around NaN by @adriangonz in #1346
• Address flakiness on 'mlserver build' tests by @adriangonz in #1363
• Bump Poetry and lockfiles by @adriangonz in #1369
• Bump Miniforge3 to 23.3.1 by @adriangonz in #1372
• Re-generate License Info by @github-actions in #1373
• Improved huggingface batch logic by @ajsalow in #1336
• Add inference params support to MLFlow's custom invocation endpoint (… by @M4nouel in #1375
• Increase build space for runtime builds by @adriangonz in #1385
• Fix minor typo in sklearn README by @krishanbhasin-gc in #1402
• Add catboost classifier support by @krishanbhasin-gc in #1403
• added model_kwargs to huggingface model by @nanbo-liu in #1417
• Re-generate License Info by @github-actions in #1456
• Local response cache implementation by @SachinVarghese in #1440
• fix link to custom runtimes by @kretes in #1467
• Improve typing on Environment class by @krishanbhasin-gc in #1469
• build(dependabot): Change reviewers by @jesse-c in #1548
• MLServer changes from internal fork - deps and CI updates by @sakoush in #1588

New Contributors

• @vtaskow made their first contribution in #1281
• @lc525 made their first contribution in #1286
• @strickvl made their first contribution in #1289
• @ramonpzg made their first contribution in #1315
• @jesse-c made their first contribution in #1337
• @ajsalow made their first contribution in #1336
• @M4nouel made their first contribution in #1375
• @nanbo-liu made their first contribution in #1417
• @kretes made their first contribution in #1467

Full Changelog: 1.3.5...1.4.0

1.3.5

What's Changed

• Rename HF codec to hf by @adriangonz in #1268
• Publish is_drift metric to Prom by @joshsgoldstein in #1263

New Contributors

• @joshsgoldstein made their first contribution in #1263

Full Changelog: 1.3.4...1.3.5

1.3.4

What's Changed

• Silent logging by @dtpryce in #1230
• Fix mlserver infer with BYTES by @RafalSkolasinski in #1213

New Contributors

• @dtpryce made their first contribution in #1230

Full Changelog: 1.3.3...1.3.4

1.3.3

What's Changed

• Add default LD_LIBRARY_PATH env var by @adriangonz in #1120
• Adding cassava tutorial (mlserver + seldon core) by @edshee in #1156
• Add docs around converting to / from JSON by @adriangonz in #1165
• Document SKLearn available outputs by @adriangonz in #1167
• Fix minor typo in alibi-explain tests by @ascillitoe in #1170
• Add support for .ubj models and improve XGBoost docs by @adriangonz in #1168
• Fix content type annotations for pandas codecs by @adriangonz in #1162
• Added option to configure the grpc histogram by @cristiancl25 in #1143
• Add OS classifiers to project's metadata by @adriangonz in #1171
• Don't use qsize for parallel worker queue by @adriangonz in #1169
• Fix small typo in Python API docs by @krishanbhasin-gc in #1174
• Fix star import in mlserver.codecs.* by @adriangonz in #1172

New Contributors

• @cristiancl25 made their first contribution in #1143
• @krishanbhasin-gc made their first contribution in #1174

Full Changelog: 1.3.2...1.3.3

1.3.2

What's Changed

• Use default initialiser if not using a custom env by @adriangonz in #1104
• Add support for online drift detectors by @ascillitoe in #1108
• added intera and inter op parallelism parameters to the hugggingface … by @saeid93 in #1081
• Fix settings reference in runtime docs by @adriangonz in #1109
• Bump Alibi libs requirements by @adriangonz in #1121
• Add default LD_LIBRARY_PATH env var by @adriangonz in #1120
• Ignore both .metrics and .envs folders by @adriangonz in #1132

New Contributors

• @ascillitoe made their first contribution in #1108

Full Changelog: 1.3.1...1.3.2