TensorFlow Recommenders Addons v0.7.0
Release Notes
This is the 7th release of TensorFlow Recommenders-Addons
Main Features:
- [Feat] Support unique in FieldWiseEmbedding and SquashedEmbedding by @rhdong in #311
- [Feat] Add tf-serving config shell script by @rhdong in #339
- [feat] Added support for Tensorflow2 strategy distributed training and Horovod AllToAll synchronous distributed training. by @MoFHeka in #347
- Fix some typing errors by @fuhailin in #354
- [feat] Make saving model more easier when using HvdAllToAllEmbedding by adding save function overwriting patch in tf_save_restore_patch.py. by @MoFHeka in #362
- [Feat] Compatible with Tensorflow later than version 2.11.0. by @MoFHeka in #331
- [feat] Support for HKV by adding HKV source code by @LinGeLin in #377
- [Feature] Compatible with TensorFlow 2.13 and below. Also fix some HKV feature. by @MoFHeka in #378
- [Feat] Compatible with TensorFlow 2.15 by @MoFHeka in #386
- [Feat] Add bfloat16 value type support in Redis and CPU table backend. by @MoFHeka in #419
- [feat] Add macOS Apple Silicon pipeline by @poinwater in #422
- [Feat] Try to compatible with Keras 3 optimizer design and support CUDNN 9.0+. by @MoFHeka in #392
- [FEA]Support more hkv strategy by @LinGeLin in #389
- [FEA]add reserved_key_start_bit option to config hkv by @jq in #408
- [FEA]expose ragged_embedding_ops for safe_embedding_lookup_sparse by @jq in #410
Bug Fixs:
[fix] fix some core dump cases and make usage of CUDA streams more reasonable. Also fix ineffective checkpoint setting. by @MoFHeka in #328
- Fix: de.save_to_file_system not work in estimator by @PWZER in #329
- [fix]fix synchronous trainging error for redis backend by @fuhailin in #360
- [Fix] fix bugs when loading KV files and more. Also make horovod saving function is callable independent bug not patched origin save function. by @MoFHeka in #364
- [fix] DEHvdCheckpoint failed when importing Horovod unsuccessfully. by @MoFHeka in #372
- [Fix] Support TF CheckpointManager in 2.9. And support create Checkpoint with custom model key. by @MoFHeka in #373
- [Fix] CheckpointManager couldn't work properly and KV files couldn't be restored when user using a lazy build Keras model. by @MoFHeka in #374
- [Fix] Several bugs when using HvdAllToAllEmbedding to train model and save/restore KV files. by @MoFHeka in #376
- [fix] Change the parameter max_capacity sent by the cuckoo gpu api to… by @LinGeLin in
- [fix] Fixed setting FileSystemSaver buffer_size does not take effect by @LinGeLin in #384
- [Fix] Compiling error in TF2.13 by @MoFHeka in #396
- [fix] Supported hkv cpu operator base cuckoo cpu operator by @LinGeLin in #387
- [fix] forgot to pass hvd_rank parameter inner a check function of _de_keras_save_func. by @MoFHeka in #398
- [fix] fixed hkv cuda misalign in tf2.15 by @LinGeLin in #399
- [fix] Fixed buffer_size setting when hkv loads and saves files by @LinGeLin in #400
- [Fix] remove .numpy which failed in gpu/distributed env by @jq in #404
- [Fix] Compatible with TF2.15 register_checkpoint_saver when multiple TFRA Embedding in one trackables. by @MoFHeka in #403
- [Fix] Stack overflow in Redis Backend and RestrictPolicy couldn't be saved when using DE embedding layer. by @MoFHeka in #415
- fix version check by @jq in #416
What's Changed
- [CI] switch the version to 0.6.0 and update readme by @rhdong in #314
- Adding the notebook for dynamic_embedding demo by @thushv89 in #315
- [CI] clear CI cache folder and reduce size of CI docker img by @rhdong in #333
- [Doc] serving with triton by @lixiang-repo in #346
- [CI] Add .bazelversion file by @fuhailin in #355
- [build] Disable EV build by @poinwater in #357
- [Refactor]removed a build warning by @LinGeLin in #359
- [CICD]Enhance project's compatibility by @poinwater in #361
- [opt] Optimize memory usage when saving and loading hkv by @LinGeLin in #383
#382 - [CI]Switch tf version to 2.15.0 by @jq in #388
- [CI] running GPU CI on self-hosted runnners. by @rhdong in #395
- enable ShadowVariable look up for safe_embedding_lookup_sparse by @jq in #397
- [CICD] update dev container by @rhdong in #402
- [opt] set retry_on_failure to false for tf allocator by @LinGeLin in #407
- [CI] Silence the warning during pytest by @jq in #421
Thanks to our Contributors
@fuhailin, @jq, @LinGeLin, @lixiang-repo, @MoFHeka, @poinwater, @PWZER, and @rhdong
New Contributors
- @thushv89 made their first contribution in #315
- @PWZER made their first contribution in #329
- @lixiang-repo made their first contribution in #346
- @fuhailin made their first contribution in #354
- @jq made their first contribution in #388
Full Changelog: v0.6.0...v0.7.0