Sourced from keras's releases.

Keras 3.11.0

What's Changed

• Add int4 quantization support.
• Support Grain data loaders in fit()/evaluate()/predict().
• Add keras.ops.kaiser function.
• Add keras.ops.hanning function.
• Add keras.ops.cbrt function.
• Add keras.ops.deg2rad function.
• Add keras.ops.layer_normalization function to leverage backend-specific performance optimizations.
• Various bug fixes and performance optimizations.

Backend-specific changes

JAX backend

• Support NNX library. It is now possible to use Keras layers and models as NNX modules.
• Support shape -1 for slice op.

TensorFlow backend

• Add support for multiple dynamic dimensions in Flatten layer.

OpenVINO backend

• Add support for over 30 new backend ops.

New Contributors

• @​adar21a made their first contribution in keras-team/keras#21275
• @​Phil2852 made their first contribution in keras-team/keras#21304
• @​dayo09 made their first contribution in keras-team/keras#21340
• @​iazzi made their first contribution in keras-team/keras#21370
• @​timovdk made their first contribution in keras-team/keras#21385
• @​mohiuddin-khan-shiam made their first contribution in keras-team/keras#21392
• @​p-wysocki made their first contribution in keras-team/keras#21317
• @​Gayathri-K-Binoy made their first contribution in keras-team/keras#21493

Full Changelog: https://github.com/keras-team/keras/compare/v3.10.0...v3.11.0

Keras 3.10.0

New features

• Add support for weight sharding for saving very large models with model.save(). It is controlled via the max_shard_size argument. Specifying this argument will split your Keras model weight file into chunks of this size at most. Use load_model() to reload the sharded files.
• Add optimizer keras.optimizers.Muon
• Add image preprocessing layer keras.layers.RandomElasticTransform

... (truncated)

• 7bf852c Update flax (#21527)
• 4085046 [OpenVINO backend] fix openvino model exported names to match keras names (#2...
• 6bc6203 Fix a few typos in comments (#21525)
• 8bf6a58 Add VectorizedMap op class. (#21516)
• 7cb0e48 update python version (#21517)
• 7b9ab6a Fix: UpSampling2D bilinear set_image_data_format(channels_first) bug (#21456)
• 90c8da6 Fix _can_use_flash_attention. (#21512)
• e704b46 fix torch module wrapper serialization error (#21505)
• a8c245f fix TAP test (#21515)
• c9383e2 Keras <> NNX integration (#21252)
• Additional commits viewable in compare view

You can trigger Dependabot actions by commenting on this PR:

• @dependabot rebase will rebase this PR
• @dependabot recreate will recreate this PR, overwriting any edits that have been made to it
• @dependabot merge will merge this PR after your CI passes on it
• @dependabot squash and merge will squash and merge this PR after your CI passes on it
• @dependabot cancel merge will cancel a previously requested merge and block automerging
• @dependabot reopen will reopen this PR if it is closed
• @dependabot close will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually
• @dependabot show <dependency name> ignore conditions will show all of the ignore conditions of the specified dependency
• @dependabot ignore this major version will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this minor version will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)
• @dependabot ignore this dependency will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)
  You can disable automated security fix PRs for this repo from the Security Alerts page.