Bump keras from 2.13.1 to 3.12.0

[dependabot[bot]]

Bumps keras from 2.13.1 to 3.12.0.

Release notes

Sourced from keras's releases.

Keras 3.12.0

Highlights

Keras has a new model distillation API!

You now have access to an easy-to-use API for distilling large models into small models while minimizing performance drop on a reference dataset -- compatible with all existing Keras models. You can specify a range of different distillation losses, or create your own losses. The API supports multiple concurrent distillation losses at the same time.

Example:

# Load a model to distill
teacher = ...
# This is the model we want to distill it into
student = ...
Configure the process
distiller = Distiller(
teacher=teacher,
student=student,
distillation_losses=LogitsDistillation(temperature=3.0),
)
distiller.compile(
optimizer='adam',
loss='sparse_categorical_crossentropy',
metrics=['accuracy']
)
Train the distilled model
distiller.fit(x_train, y_train, epochs=10)

Keras supports GPTQ quantization!

GPTQ is now built into the Keras API. GPTQ is a post-training, weights-only quantization method that compresses a model to int4 layer by layer. For each layer, it uses a second-order method to update weights while minimizing the error on a calibration dataset.

Learn how to use it in this guide.

Example:

model = keras_hub.models.Gemma3CausalLM.from_preset("gemma3_1b")
gptq_config = keras.quantizers.GPTQConfig(
    dataset=calibration_dataset,
    tokenizer=model.preprocessor.tokenizer,
    weight_bits=4,
    group_size=128,
    num_samples=256,
    sequence_length=256,
    hessian_damping=0.01,
    symmetric=False,
</tr></table> 

... (truncated)

Commits

• adbfd13 Add warning to set_backend and more detailed example. (#21787)
• 70598b7 Fix typo in Distiller docstring
• eecd34f Fix: keras.ops.quantile works with tf graph execution (#21782)
• c2bc6cf Suport keras.op.view() to view the same data bitwise at a new dtype (#21763)
• 10b51ce Make confusion metrics compilable. (#21775)
• 18f79d6 Fix negative index handling in MultiHeadAttention attention_axes (#21721)
• 18e0364 Support for extracting volume patches (#21759)
• dc5e42c fix sas metrics in jax fit (#21765)
• 1ba3b8f Fix discretization discrepancy (#21769)
• 53987a7 Document that set_backend requires re-importing keras. (#21764)
• Additional commits viewable in compare view

Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting @dependabot rebase.

---

Dependabot commands and options

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.