Sourced from keras's releases.

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
• Add loss function keras.losses.CategoricalGeneralizedCrossEntropy (with functional version keras.losses.categorical_generalized_cross_entropy)
• Add axis argument to SparseCategoricalCrossentropy
• Add lora_alpha to all LoRA-enabled layers. If set, this parameter scales the low-rank adaptation delta during the forward pass.
• Add activation function keras.activations.sparse_sigmoid
• Add op keras.ops.image.elastic_transform
• Add op keras.ops.angle
• Add op keras.ops.bartlett
• Add op keras.ops.blackman
• Add op keras.ops.hamming
• Add ops keras.ops.view_as_complex, keras.ops.view_as_real

PyTorch backend

• Add cuDNN support for LSTM with the PyTorch backend

TensorFlow backend

• Add tf.RaggedTensor support to Embedding layer
• Add variable-level support for synchronization argument

OpenVINO backend

• Add support for over 50 additional Keras ops in the OpenVINO inference backend!

New Contributors

• @​JyotinderSingh made their first contribution in keras-team/keras#20993
• @​SaifMohammed22 made their first contribution in keras-team/keras#20982
• @​11happy made their first contribution in keras-team/keras#20940
• @​jpy794 made their first contribution in keras-team/keras#21008
• @​chiruu12 made their first contribution in keras-team/keras#20950
• @​arkhamHack made their first contribution in keras-team/keras#21010
• @​samitshah1 made their first contribution in keras-team/keras#21036
• @​nathanrooy made their first contribution in keras-team/keras#21056
• @​rfezzani made their first contribution in keras-team/keras#21053
• @​drasmuss made their first contribution in keras-team/keras#21072
• @​pass-lin made their first contribution in keras-team/keras#21037
• @​wilsbj made their first contribution in keras-team/keras#21077
• @​timsweeneyfanelli made their first contribution in keras-team/keras#21081
• @​darshil929 made their first contribution in keras-team/keras#21042
• @​superbobry made their first contribution in keras-team/keras#21106
• @​nithin9000 made their first contribution in keras-team/keras#21136
• @​Huanli-Gong made their first contribution in keras-team/keras#21141
• @​he7d3r made their first contribution in keras-team/keras#21098

... (truncated)

• 3bedb9a Update layer.py add_metric error message (#21290)
• c52d71e [OpenVINO Backend] support ops.split (#21296)
• 8f67bab Update layer.py add_loss to properly handle when input loss is a list of scal...
• df58e70 jax eig now has GPU support
• c6187c1 [OpenVINO Backend] modify ops.stack to support tuples (#21297)
• c2b1993 Replace the bias addition in EinsumDense with ops.add(x, bias) instead of usi...
• c949e75 Implementation np.outer function (#21270)
• cf08b92 Revert "Add sparse support to ops.ones_like and ops.zeros_like." (#21302)
• dba71da update JAX GPU version (#21293)
• e19a2ed Add an easy way to run a script for a few steps only (#21217)
• 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)