DJL v0.36.0 Release

What's Changed

• Increase build version to 0.36.0 by @access2rohit in #3817
• Update the Documentation (via DocString) to indicate the risks of using Utils.openUrl() with untrusted inputs by @access2rohit in #3819
• NDManager.create(Number) unsupported type error message improvement by @fracpete in #3818

New Contributors

• @access2rohit made their first contribution in #3816
• @fracpete made their first contribution in #3818

Full Changelog: v0.35.1...v0.36.0

DJL v0.35.1 Release

What's Changed

• fix: upgrade jQuery from 2.1.1 to 3.7.1 to address security vulnerabilities by @Lokiiiiii in #3812
• Fix script injection vulnerabilities in GitHub Actions workflows by @Lokiiiiii in #3813
• Fix security vulnerabilities in QuestionAnsweringTranslator (CVSS 8.2) by @Lokiiiiii in #3814

New Contributors

• @Lokiiiiii made their first contribution in #3812

Full Changelog: v0.35.0...v0.35.1

DJL v0.35.0 Release

What's Changed

• Engine Updates
  • XGBoost 3.0.4 #3788

Enhancements

• Increase build version to 0.35.0 by @xyang16 in #3766
• Add default header for openai by @bryanktliu in #3772
• Update gradle to 9.0.0 by @xyang16 in #3777
• [XGBoost] Support json model for XGBoost by @xyang16 in #3786
• [api] Accept json input/output for tensor input by @xyang16 in #3787
• Upgrade xgboost to 3.0.4 by @xyang16 in #3788
• [pytorch] Add tuple of dict support for IValue by @xyang16 in #3797
• [XGBoost] Add back gpu support for xgboost by @xyang16 in #3796
• Update gradle build script to support configuration cache by @xyang16 in #3782
• Added percentile implementation for Pytorch engine by @tipame in #3800
• Implemented CSV translator that handles CSV input/output support for XGBoost by @smouaa in #3801
• Correct topK documentation by @alanocallaghan in #3808
• [api] Refactor csvTranslator by @xyang16 in #3805

Bug Fixes

• Fix pytorch native 2.5.1 aarch64 build by @xyang16 in #3767
• [fix] Fixes load tokenizer gpu shared library issue by @xyang16 in #3773
• Fixes #3774 for YoloSegmentationTranslator by @bryanktliu in #3775
• Fixes issue #3761 by @bryanktliu in #3776
• Fix BaseNDManager.debugDump by @petebankhead in #3780
• Fix preference of tokenizer_config.json and remove doLowerCase from TokenizerConfig by @Soha-Agarwal in #3785
• Fixes: #3795, adds aggregation_strategy to token classification task by @bryanktliu in #3798
• Fix pytorch native build for windows by @xyang16 in #3802

CI/CD

• Build pytorch jni cpu precxx by @xyang16 in #3770
• Remove pytorch 2.1.2 and 2.3.1 publish in nightly by @xyang16 in #3771
• Fix sentencepiece native workflow by @xyang16 in #3768
• Fix fasttext native workflow by @xyang16 in #3769
• Fix continuous build by @xyang16 in #3804

New Contributors

• @smouaa made their first contribution in #3801
• @alanocallaghan made their first contribution in #3808

Full Changelog: v0.34.0...v0.35.0

DJL v0.34.0 Release

Key Changes

• Engine Updates
  • PyTorch 2.7.1 #3733
  • Remove TensorRT engine #3765

Enhancements

• [api] Adds FUSE based repository support by @raymondkhliu in #3695
• Treat model server as a remote model by @xyang16 in #3704
• Align ZeroShotClassificationTranslator with Hugging Face behavior by @raphaeldelio in #3712
• Remove usage of UUID.randomUUID() for better performance by @aakashb-kayzen in #3719
• Replace UUID with NDManager.nextUid() by @xyang16 in #3720
• Add NDArray diagonal by @dev-jonghoonpark in #3724
• [api] Implements remote REST API call as a model by @bryanktliu in #3725
• Adds jsonlines streaming support for RpcEngine by @bryanktliu in #3727
• Adds genai extension by @bryanktliu in #3726
• [genai] tool calls to ChatInput by @bryanktliu in #3728
• Add utility class for genai function call by @bryanktliu in #3729
• Improve function call for genai extension by @bryanktliu in #3731
• Support convert ChatInput to GeminiInput by @bryanktliu in #3739
• Add partial support for HuggingFace Tokenizer to use parameters from tokenizer_config.json by @Soha-Agarwal in #3738
• Add Anthropic support from genai by @bryanktliu in #3759

Bug Fixes

• Correct CaptchaDataset options count to prevent torch.gather IndexError by @xinhuagu in #3694
• Fix dimension check when reshaping offsets in SeqBatcher by @xinhuagu in #3702
• Fix the incorrect function name and minor typo in doc by @xinhuagu in #3703
• Fix incorrect return value in getImageHeight method by @xinhuagu in #3706
• [djl_converter]: Fixes djl_converter bug by @raymondkhliu in #3705
• Fix the out of bounds exception when using an init image by @luke-zhou in #3717
• Fix earlystopping metric issue #3722 by @SamBSalgado in #3736
• [tokenizers] Fix tokenizer cpu and cuda build by @xyang16 in #3756
• [examples] Update tfhub urls by @xyang16 in #3752
• Update tfhub repository url by @xyang16 in #3755

Documentation

• [docs] Update model zoo document by @xyang16 in #3690

CI/CD

• increase build version to 0.34.0 by @siddvenk in #3689
• Uses new recommended way to build pip wheel by @raymondkhliu in #3709
• Bump protobuf from 3.20.2 to 4.25.8 in /extensions/tokenizers/src/main/python by @dependabot[bot] in #3716
• [android] Upgrade DJL version to 0.34.0 by @xyang16 in #3721
• [ci] simplify nightly publish workflow by @xyang16 in #3732
• [ci] Update maven central publish url and credential by @xyang16 in #3748
• [djl-converter] Update license in pyproject.toml by @xyang16 in #3749
• [pytorch] Updates PyTorch to 2.7.1 by @xyang16 in #3733
• [ci] Remove serving-publish workflow by @xyang16 in #3750
• Update oss sonatype snapshot repository url by @xyang16 in #3754
• Upgrade dependency versions by @xyang16 in #3762
• [android] Upgrade pytorch version to 2.7.1 by @xyang16 in #3763
• [ci] Add post-publish task by @xyang16 in #3764
• Increase DJL version to 0.34.0 by @Soha-Agarwal in #3758

New Contributors

• @raymondkhliu made their first contribution in #3695
• @raphaeldelio made their first contribution in #3712
• @luke-zhou made their first contribution in #3717
• @aakashb-kayzen made their first contribution in #3719
• @dev-jonghoonpark made their first contribution in #3724
• @Soha-Agarwal made their first contribution in #3738
• @SamBSalgado made their first contribution in #3736

Full Changelog: v0.33.0...v0.34.0

DJL v0.33.0 Release

Key Changes

• Engine Updates
  • OnnxRuntime Updated to 1.21.0

Enhancements

• [tokenizers] Add lasttoken pooling by @xyang16 in #3607
• [api] Provide concrete implementation of TranslatorContext by @xyang16 in #3622
• [api] Add zero shot object detection support by @xyang16 in #3626
• [api] Adds zero short image classification support by @xyang16 in #3628
• Adds yolov8s-world2 model support by @xyang16 in #3637
• [tensorflow] Allow retrieving available signatures for TensorFlow models by @xyang16 in #3638
• [api] Improve listModel performance by @xyang16 in #3641
• [tokenizers] Adds SparseRetrievalTranslator by @xyang16 in #3642
• [tokenizers] Fix tokenizer name in tests by @xyang16 in #3652
• [tokenizer] Updates tokenizers to 0.21.1 by @xyang16 in #3654
• [onnxruntime] Updates OnnxRuntime to 1.21.0 by @xyang16 in #3678
• [examples] Add WhisperJet model demo by @xyang16 in #3681
• [pytorch] Add diff support by @saedmanaf in #3663

Bug Fixes

• [examples] fixing some dependencies and test requirements by @sindhuvahinis in #3605
• [onnxruntime] Fixes intraOpNumThreads bug by @xyang16 in #3630
• [ci] Fixes build.gradle for integration by @xyang16 in #3635
• [ci] Fixes system properties in gradle build script by @xyang16 in #3636
• Fix: Corrected 16-bit PCM normalization to avoid overflow issue by @leleZeng in #3646
• Fix rust build with update candle-core the 0.8.4 version by @xyang16 in #3645
• Fixed rust build with update candle-core the 0.8.4 version by @xyang16 in #3649
• [fix] LRUReplayBuffer "stepToReplace" index fix by @dwctic in #3660

Documentation

• docs: added a link to the continuous badge by @operagxoksana in #3668
• [doc] Update onnxruntime readme by @xyang16 in #3669
• chore: edited badges by @operagxoksana in #3670
• chore: added an icon to the release by @operagxoksana in #3671
• Correct 'Load Model' documentation: method ImageClassificationTranslator.builder().setSynsetArtifactName() does not exist by @xinhuagu in #3677

CI/CD

• [release] Release DJL 0.32.0 by @sindhuvahinis in #3603
• bump build version to 0.33.0 by @siddvenk in #3627
• [ci] Upgrade gradle to 8.13 by @xyang16 in #3650
• [ci] Fixes CI build for cmake 4.0.0 by @xyang16 in #3659
• Bump openssl from 0.10.71 to 0.10.72 in /extensions/tokenizers/rust by @dependabot in #3661
• update some dependency versions by @siddvenk in #3665
• remove status from log4j configuration of status logger by @siddvenk in #3667
• Remove unnecessary exclusion for testng by @xyang16 in #3687
• Updates dependencies version by @xyang16 in #3688
• [onnx] use zulu jdk to fix windows issues by @siddvenk in #3683
• [onnx] fix one more usage of java distribution to zulu for windows by @siddvenk in #3684

New Contributors

• @leleZeng made their first contribution in #3646
• @dwctic made their first contribution in #3660
• @saedmanaf made their first contribution in #3663
• @xinhuagu made their first contribution in #3677

Full Changelog: v0.32.0...v0.33.0

DJL v0.32.0 Release

Key Changes

• Engine Updates
  • Tokenizers updated to 0.21.0
  • OnnxRuntime updated to 1.20.0

Enhancements

• [pytorch] support pytorch 2.1.2 for Neuron by @siddvenk in #3542
• [onnxruntime] Updates OnnxRuntime engine to 1.20.0 by @xyang16 in #3549
• [tokenizers] Return detail for QA inference by @xyang16 in #3555
• [api] Allows to configure custom batchifer by @xyang16 in #3559
• [tokenizer] Updates huggingface tokenizer to 0.21.0 by @xyang16 in #3572
• [tokenizers] Add int32 option to encoding by @xyang16 in #3571
• [api] Adds ZeroShotClassification support by @bryanktliu in #3579
• [tokenizers] Support import zero-shot-classification to model zoo by @bryanktliu in #3580
• [FASTTEXT] Adds linux-aarch64 support by @iamshubhambhola in #3584
• Expose OnnxRuntime's getMetadata() in DJL API by @VanjaRadulovic in #3596
• [api] Refactor image processing by @xyang16 in #3588
• Adds zero-shot-classification to model zoo by @xyang16 in #3589
• [api] Adds Pad image transform for CV by @xyang16 in #3593

Bug Fixes

• [api] fix issue in Tar/Zip Utils that resulted in incorrect artifact … by @siddvenk in #3544
• [tokenizer] fixes token_classification import issues by @bryanktliu in #3570
• [tokenizer] fixes trust_remote_code issues for DJL converter by @bryanktliu in #3569
• [fix] Fix YoloV8Translator by @xyang16 in #3575
• [tokenizers] Fixes ZeroShotClassificationTranslator bug by @bryanktliu in #3581
• [xgb] Fix xgb intern to close replaced array by @ewan0x79 in #3558

Documentation

• [pytorch] Update supported versions of pytorch for 0.32.0 by @siddvenk in #3541
• Update README.md (fix typo) by @paulk-asert in #3576
• Docs: (Readme) by @Lubov66 in #3577

CI/CD

• Increase build version to 0.32.0 by @siddvenk in #3540
• [ci] fix ci to test windows properly by @siddvenk in #3543
• [ci] adding back serving.publish to DJL by @sindhuvahinis in #3551
• [ci] adding back serving.publish to DJL by @sindhuvahinis in #3551
• [djl-convert] Remove onnxruntime from djl-convert requirements.txt by @xyang16 in #3550
• [djl-convert] Remove onnxruntime from djl-convert requirements by @xyang16 in #3552
• Fixes java23 compile error by @xyang16 in #3556
• [fix][ci] don't compile fasttext jni for windows by @siddvenk in #3590
• [ci] Upgrade gradle to 8.12 by @xyang16 in #3573
• [ci][docs] enable debug logging for s3 commands to troubleshoot failu… by @siddvenk in #3591
• [ci] Update upload-artifact action to v4 by @xyang16 in #3594
• [fix] Fix the pytorch-native ci failure by @xyang16 in #3595
• [ci] Fix nightly publish upload artifact name by @xyang16 in #3597
• Implement NDArray.sub operation by @xyang16 in #3598
• [ci] Fix continuous ci failure by @xyang16 in #3599
• [ci] Fix ClipModelTest assertion failure by @sindhuvahinis in #3602

New Contributors

• @paulk-asert made their first contribution in #3576
• @Lubov66 made their first contribution in #3577
• @iamshubhambhola made their first contribution in #3584
• @VanjaRadulovic made their first contribution in #3596

Full Changelog: v0.31.1...v0.32.0

DJL v0.31.1 Release

Key Changes

• Engine Updates:
  • PyTorch 2.5.1 #3517
  • HuggingFace Tokenizers 0.20.3 #3514
• Added Android support for HuggingFace Tokenizers @naveen521kk in #3531
• Fixed issue with cross-platform archive extraction #3544

Enhancements

• [api] Use encoder/decoder for Segment anython2 translator by @frankfliu in #3487
• [api] alternative NDArray should not be closed in NDScope by @frankfliu in #3490
• [api] Adds sam2 model to onnxruntime model zoo by @frankfliu in #3492
• [api] Standardizes CV output format by @frankfliu in #3493
• [api] Visualize sam2 output for Sam2ServingTranslator by @frankfliu in #3494
• [api] Improve Sam2Translator for PyTorch traced model by @frankfliu in #3495
• [android] Update pytorch version to 2.4.0 by @xyang16 in #3474
• [tokenizers] Use tokenizers from rust.io by @xyang16 in #3476
• [rust] Remove unnecessary clone in cublaslt by @xyang16 in #3482
• [api] Makes Sam2 input consistent with other CV model by @frankfliu in #3498
• [api] Adds serving support for some CV models by @frankfliu in #3499
• HuggingFaceTokenizer: add support for Android by @naveen521kk in #3531
• [tokenizer] Updates tokenizer to 0.20.3 by @xyang16 in #3514
• [tokenizer] Updates tokenizer to 0.20.3 in libs.versions.toml by @xyang16 in #3515
• [pytorch] Adds Yolo11 model to model zoo by @xyang16 in #3516
• [pytorch] Updates PyTorch to 2.5.1 by @xyang16 in #3517
• [converter] Trim jit output token_str by @xyang16 in #3527

Bug Fixes

• [PyTorch] Fixes sam2 model version by @frankfliu in #3496
• [api] Fixes QaServingTranslator output format by @frankfliu in #3500
• [djl-convert] Fix huggingface converter by @xyang16 in #3505

Documentation

• [docs] Updates PyTorch engine README for 2.4.0 by @frankfliu in #3472
• Docs: Added a link by @operagxoksana in #3510
• [doc] Add blogposts index to docs by @xyang16 in #3519
• [doc] Add blogposts link to README by @xyang16 in #3520
• add lmi breaking changes document to docs site by @siddvenk in #3529
• Update troubleshooting.md - UnsatisfiedLinkError issue by @ThiloteE in #3512

CI/CD

• [fix][ci] configure aws creds manually to avoid node20 issues on inco… by @siddvenk in #3469
• [ci] Updates gradle to 8.10.1 by @frankfliu in #3470
• [ci] configure aws creds manually to avoid node20 issues for AL2 by @frankfliu in #3471
• [ci] Update tensorrt native build container by @xyang16 in #3477
• [ci] Fixes fasttext native build for nodejs20 issue by @xyang16 in #3478
• [ci] Fixes sentencepiece native build for nodejs20 issue by @xyang16 in #3479
• Increase build version to 0.31.0 by @xyang16 in #3475
• [mxnet] Fixes build error on JDK 22 by @frankfliu in #3485
• [ci] Fixes java 21 compile error by @frankfliu in #3497
• Delete serving publish from DJL repo by @brndysgit in #3501
• Bump com.google.protobuf:protobuf-java from 3.25.4 to 3.25.5 by @dependabot in #3502
• dependency updates for djl by @siddvenk in #3528
• Add CI for the hugging face tokenizers android by @naveen521kk in #3532
• CI: setup cargo-ndk for huggingface tokenizers android builds by @naveen521kk in #3535
• update DJL version to 0.31.0 in docs by @siddvenk in #3534
• Fix a typo in android/tokenizer-native/build.gradle by @naveen521kk in #3537
• fix dependency versions in examples/pom.xml by @siddvenk in #3539
• [android] fix djl version for android by @siddvenk in #3526

New Contributors

• @brndysgit made their first contribution in #3501
• @operagxoksana made their first contribution in #3510
• @ThiloteE made their first contribution in #3512
• @naveen521kk made their first contribution in #3531

Full Changelog: v0.30.0...v0.31.1

DJL v0.30.0 Release

Key Changes

• Engine Updates:
  • OnnxRuntime 1.19.0 #3446
  • Huggingface Tokenizers 0.20.0 #3452
• Added mask generation task for SAM2 model #3450
• Text Embedding Inference:
  • Added Mistral, Qwen2, GTE, Camembert embedding model support
  • Added reranker model support

Enhancement

• [api] Avoid non-ascii characters by @frankfliu in #3395
• [djl-converter] Exit with error if convert model failed by @frankfliu in #3399
• [api] Support TEI input format to reranking model by @frankfliu in #3400
• [rust] Adds sigmoid and softmax operator for Rust engine by @frankfliu in #3407
• [test] Detect GPUs with specified engine by @frankfliu in #3409
• [api] Adds Criteria.isDownload() api by @frankfliu in #3403
• [rust] Build .so file for each cuda arch by @frankfliu in #3410
• [rust] Add mistral embedding model by @xyang16 in #3412
• [tokenizers] Add supported arch in djl-convert by @xyang16 in #3416
• [tokenizers] Replace pt file names to safetensors by @xyang16 in #3417
• [rust] Load model on given device by @xyang16 in #3419
• [rust] Add qwen2 model by @xyang16 in #3420
• [rust] Support pre-downloaded rust shared library by @frankfliu in #3421
• [pytorch] Adds pad operator by @frankfliu in #3423
• [rust] Provides better error message for unsupported ops by @frankfliu in #3424
• [api] Adds center fit image operation for Yolo by @frankfliu in #3425
• [rust] Add GTE and Gemma2 model by @xyang16 in #3422
• [djl-convert] Sets default max model size limit for importing by @frankfliu in #3428
• [djl-import] Includes requires version when importing model by @frankfliu in #3431
• [android] Upgrade DJL version to 0.30.0 by @xyang16 in #3432
• [rust] Make cublaslt wrapper non static by @xyang16 in #3434
• [djl-convert] Exclude models in includeTokenTypes by @xyang16 in #3435
• [rust] Make tensor contiguous in rotary embedding by @xyang16 in #3436
• [rust] Allows -1 dim for normalize() by @xyang16 in #3442
• Refactored Identifiers by @congyuluo in #3381
• [rust] Adds text classification models to Rust model zoo by @frankfliu in #3444
• [examples] Adds segment anything 2 example by @frankfliu in #3449
• [api] Refactor ImageFeatureExtractor by @frankfliu in #3455
• [api] Adds base64 image support for ImageTranslator by @frankfliu in #3456
• [djl-import] Improve model import speed by @frankfliu in #3457
• [api] Updates dependencies version to latest by @frankfliu in #3454
• [api] Optimized text embedding post processing performance by @frankfliu in #3459
• add drawMarks to android BitMapImageFactory by @sindhuvahinis in #3460
• [ci] moving to temporary iam credentials for publishing steps by @siddvenk in #3462
• [OnnxRuntime] Update debug log message by @frankfliu in #3463
• Increase DJL version to 0.30.0 by @xyang16 in #3465
• [examples] Adds gradle tasks for each example by @frankfliu in #3466
• Upgrade dependency versions by @xyang16 in #3467
• [tokenizers] Converting encoding to int32 NDList by @xyang16 in #3468

Bug Fixes

• [api] Fixes logging calling convention by @frankfliu in #3394
• [djl-converter] Fixes import text embedding model from local folder by @frankfliu in #3388
• [djl-converter] Fixes djl-convert command line return code by @frankfliu in #3406
• [rust] Fix camembert and distilbert model loading by @xyang16 in #3415
• [rust] Fix camembert model loading by @xyang16 in #3418
• [rust] Fixes memory leak by @frankfliu in #3433
• [djl-convert] Fixes huggingface model converter by @frankfliu in #3440
• [rust] Fix bert model classifier loading by @xyang16 in #3441
• [xgb] Fixes alternative NDArray conversion issue by @frankfliu in #3453
• [djl-import] Fixes missing arguments for onnx import by @frankfliu in #3458
• [ci][fix] use v2 for aws credentials due to glib issues with node 20 by @siddvenk in #3464

Documentation

• [examples] Moves nlp examples into nlp folder by @frankfliu in #3393
• [docs] Build versions.json before mike deploy by @Varun-Dutta in #3392
• [example] Enable PyTorch for some training example by @frankfliu in #3398
• [docs] Updates docs website url by @frankfliu in #3404
• [docs] Fixes broken links in markdown files. by @frankfliu in #3408
• [djl-import] Fixes missing trust-remote-code arg for import model zoo by @frankfliu in #3427
• [docs] Updates trace whisper model document by @frankfliu in #3426
• [tensorflow] Updates tensorflow document by @frankfliu in #3430
• [docs] Adds segment anything document by @frankfliu in #3451

CI/CD

• [ci] Fixes serving publish for awscurl release version by @frankfliu in #3411
• [ci] Remove no_response workflow by @xyang16 in #3429

Full Changelog: v0.29.0...v0.30.0

DJL v0.28.0 Release

Key Changes

• Upgrades for engines
  • PyTorch 2.2.2 #3155
  • Sentencepiece 0.2.0 #3163
• Enhancements for engines and API
  • Adds experimental Rust engine #3078

Enhancement

• [api] Automatically detect translatorFactory based on task by @frankfliu in #3136
• [api] Adds OnesBlockFactory to make it easy for testing by @frankfliu in #3140
• Ensure the alternative ND manager can use GPUs by @david-sitsky in #3138
• [api] Tries to use the same device for alternative NDManager by @frankfliu in #3146
• [api] Supports serialize NaN in json by @frankfliu in #3156
• [rust] Add rust engine implemenation by @frankfliu in #3078
• [rust] Adds Rust model zoo by @frankfliu in #3132
• [rust] Support load DJL model for RsModel by @frankfliu in #3147
• [rust] RsModel delete model in close by @xyang16 in #3170
• [tokenizers] Updates tokenizer to 0.19.1 by @frankfliu in #3143
• [tokenizer] Allows use HF_TOKEN to access gated model by @frankfliu in #3150
• [tokenizers] Create djl_converter package by @xyang16 in #3172
• [tokenizer] Refactor djl_convert python code by @frankfliu in #3179
• Updates on djl_converter by @xyang16 in #3187
• [pytorch] Updates PyTorch to 2.2.2 by @frankfliu in #3155
• [pytorch] Update PyTorch engine README for version 2.2.2 by @frankfliu in #3165
• [pytorch] optimize memory copy cost for pytorch NDArray by @ewan0x79 in #3137
• [pytorch] Updates PyTorch to 2.3.0 by @frankfliu in #3192
• [sentencepiece] Updates sentencepiece to 0.2.0 by @frankfliu in #3163
• [huggingface] Adds more option to convert onnx model by @frankfliu in #3180

Bug Fixes

• [gitignore] Avoid checking binary files. by @frankfliu in #3134
• [api] Closes file stream by @frankfliu in #3130
• [api] Fixes logging invoke convention by @frankfliu in #3148
• [api] Fixes Criteria.toString() bug by @frankfliu in #3151
• [api] Fixes tarslip issue by @frankfliu in #3075
• [examples] Fixes TextGeneration EOS bug by @frankfliu in #3177
• [tokenizer] Fixes model zoo import script by @frankfliu in #3126
• [Lgbm] fix LgbmNDArray replaced.close() release data problem by @ewan0x79 in #3174
• [rust] Fixes compile warnings by @frankfliu in #3189
• [ci] Fixes pytorch jni build for 1.13.1 by @frankfliu in #3184
• [ci] Fixes awscurl publish location by @frankfliu in #3182
• [ci] Fixes build on macOS aarch64 machine by @frankfliu in #3191
• [ci] Fixes nightly pytorch jni build by @frankfliu in #3196

Documentation

• [examples] Re-organize CV examaples by @frankfliu in #3135
• [examples] Prepare for MXNet deprecation by @frankfliu in #3157
• [doc] Removes mention of future lab by @zachgk in #3154
• [docs] Updates docs for setup java on mac by @frankfliu in #3188
• [website] Remove live demo from djl.ai web page by @frankfliu in #3171
• Fixed Typo in Docs by @fensch in #3193
• Update README.md by @elect86 in #3195

CI/CD

• [ci] Update github action runner to macOS x86_64 instance by @frankfliu in #3144
• [ci] Updates google code formatter to 1.22.0 by @frankfliu in #3149
• [ci] Upgrades gradle to 8.5 by @frankfliu in #3153
• [ci] Updates dependencies version by @frankfliu in #3164
• [ci] Adds cuda version as github actions parameter for Pytorch JNI build by @frankfliu in #3185

New Contributors

• @david-sitsky made their first contribution in #3138
• @elect86 made their first contribution in #3195

Full Changelog: v0.27.0...v0.28.0

DJL v0.29.0 Release

Key Changes

• Upgrades for engines

  • Upgrades PyTorch engine to 2.3.1
  • Upgrades TensorFlow engine to 2.16.1
  • Introduces Rust engine CUDA support
  • Upgrades OnnxRuntime version to 1.18.0 and added CUDA 12.4 support
  • Upgrades javacpp version to 1.5.10
  • Upgrades HuggingFace tokenizer to 0.19.1
  • Fixes several issues for LightGBM engine
  • Deprecated llamacpp engine

• Enhancements for engines and API

  • Adds Yolov8 segmentation and pose detection support
  • Adds metric type to Metic class
  • Improves drawJoints and drawMask behavior for CV model
  • Improves HuggingFace model importing and conversion tool
  • Improves HuggingFace NLP model batch inference performance
  • Adds built-in ONNX extension support
  • Adds several NDArray operators in PyTorch engine
  • Adds fp16 and bf16 support for OnnxRuntime engine
  • Adds CrossEncoder support for NLP models

Enhancements

• Adds metric type to Metic class by @frankfliu in #3244
• Improves drawJoints behavior by @frankfliu in #3305
• [api] Allows to control json pretty print with env var by @frankfliu in #3288
• [api] Avoid null dimensions for Metric by @frankfliu in #3246
• [api] Improve NDArray.toDebugString() output by @frankfliu in #3290
• [api] Loads native engine in deterministic order by @frankfliu in #3300
• [api] Refactor drawMask() for instance segmentation by @frankfliu in #3304
• [api] Refactor nms for yolo translator by @frankfliu in #3297
• add close method to all nd manager by @lanking520 in #3225
• ported tools/stats.gradle by @elect86 in #3219
• use standard GSON output by @lanking520 in #3284
• [enhancement] Optimize memory copy overhead to enhance performance. by @ewan0x79 in #3289
• Gradle Kotlin script plus other stuff by @elect86 in #3167
• Improved incremental build by @benjie332 in #3231
• Refactored Identifiers by @congyuluo in #3276
• Refactored Identifiers by @congyuluo in #3282
• [gradle] Remove unused gradle files by @frankfliu in #3280
• [jacoco] exclude spark extension since it doesnot contain test by @frankfliu in #3230
• [Lgbm] support multi classification by @ewan0x79 in #3234
• [Lgbm] support multi type prediction by @ewan0x79 in #3237
• [llamacpp] Removing llamacpp support in DJL by @frankfliu in #3312
• [mxnet-model-zoo] Adds missing translatorFactory in metadata by @frankfliu in #3279
• [onnx] Adds fp16 and bfp16 support for OnnxRuntime by @frankfliu in #3281
• [onnxruntime] Add debug message for OnnxRuntime by @xyang16 in #3217
• [onnxruntime] Adds yolov8n pose model for OnnxRuntime by @frankfliu in #3309
• [onnxruntime] Adds yolov8n-seg model to onnxruntime model zoo by @frankfliu in #3310
• [onnxruntime] Load onnx extenstion if available by @frankfliu in #3333
• [pytorch] Adds Yolov8n-seg model to model zoo by @frankfliu in #3308
• [pytorch] Adds back PyTorch 2.1.2 support by @frankfliu in #3285
• [pytorch] Adds yolov8n pose estimation model by @frankfliu in #3298
• [pytorch] Implements gammaln operator for PyTorch by @frankfliu in #3262
• [pytorch] Split maven publish into two parts by @frankfliu in #3273
• [rust] Add tokenizer cuda build workflow by @xyang16 in #3322
• [rust] Allows -2 as dims for sum() by @frankfliu in #3221
• [rust] Change loging level to debug by @xyang16 in #3336
• [rust] Download cu124 jni library for cuda by @xyang16 in #3327
• [rust] Remove 0-dimension tensor compare in NDArrayTests by @xyang16 in #3320
• [rust] Update gpu build pipeline to cu122 by @xyang16 in #3334
• [rust] Upgrade candle version by @xyang16 in #3248
• [rust] Use fused layer by @xyang16 in #3260
• [spark] Do not support model_url by @xyang16 in #3224
• [spark] Update dependency versions by @xyang16 in #3241
• [spark] Updates spark version to 3.5.1 by @frankfliu in #3240
• [spark] Use batch predict API by @xyang16 in #3242
• [text-embedding] Remove CrossEncoderTranslatorFactory in favor of TextEmbeddingTranslatorFactory by @frankfliu in #3239
• [tokenizer] Adds maxos-13 support back by @frankfliu in #3328
• [tokenizer] Ensure GPU is used in TextEmbeddingTranslator by @david-sitsky in #3212
• [tokenizer] Process text embedding input and output in stacked NDArray by @xyang16 in #3213
• [tokenizer] Recover accidentally deleted file by @frankfliu in #3311
• [tokenizer] Supports cross encoder for text classification model by @frankfliu in #3338
• [tokenizers] Download jni lib files for cuda by @xyang16 in #3326

Bug Fixes

• [api] Fix unitest in GPU docker running on CPU case by @frankfliu in #3228
• [api] Fixes IdEmbedding memory leak by @frankfliu in #3257
• [api] Fixes nightly tests on GPU machine by @frankfliu in #3302
• [api] Fixes unitest by @frankfliu in #3210
• [fix] fix lgbm bytebuffer native order by @ewan0x79 in #3258
• Fix Application.of missing some applications by @tadayosi in #3277
• [mxnet] Fixes GloveWordEmbeddingTranslator bug by @frankfliu in #3287
• [pytorch-model-zoo]: fix PtSsdTranslator.Builder.self() by @eversnarf in #3204
• [pytorch] Fixes PyTorch 2.3.1 windows dependencies by @frankfliu in #3269
• [pytorch] Fixes PyTorch 2.3.1 windows dependencies by @frankfliu in #3270
• [pytorch] Fixes uploadS3 gradle task by @frankfliu in #3263
• [rust] Fix NDArrayTests failure on cuda by @xyang16 in #3319
• [rust] Fix deleteModel error by @xyang16 in #3229
• [rust] Fix output tensor dtype by @xyang16 in #3249
• [rust] Fix tokenizer cuda pipeline name by @frankfliu in #3325
• [rust] Fixes test failure on GPU by @frankfliu in #3301
• [timeseries] Fixes contentLength issue for inference by @frankfliu in #3306
• [timeseries] Fixes duration format issue by @frankfliu in #3307
• [tensorrt] Fixes gradle biuld script by @frankfliu in #3253
• [tokenizer] Fixes detect include token type logic by @frankfliu in #3318
• [tokenizer] Fixes tokenizer build workflow by @frankfliu in #3323
• [tokenizers] Fixes huggingface build for Windows by @frankfliu in #3330
• [tokenizers] Fixes memory leak when there is overflowing tokens by @baldersheim in #3317
• [xgb] Fixes gradle build script by @frankfliu in #3254

Documentation

• [doc] add output formatter schema to LMI docs.djl.ai by @sindhuvahinis in #3268
• [doc] add release notes to docs.djl.ai by @sindhuvahinis in #3266
• [docs] Bump up DJL version to 0.28.0 by @frankfliu in #3247
• [docs] Update example reference by @emmanuel-ferdman in #3275
• [docs] add dark theme and fixed broken link by @Varun-Dutta in #3295
• [example] Adds PyTorch action recognition model to model zoo...