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