chore: Release main

[DeployDuck]

🤖 Automated Release PR

This PR was created by release-please to prepare the next release. Once merged:

1. A new version tag will be created
2. A GitHub release will be published
3. The changelog will be updated

Changes to be included in the next release:

training: 0.14.0

0.14.0 (2026-05-22)

⚠ BREAKING CHANGES

• aggregate losses for temporal downscaler (#1069)
• introduce mlp implementation for gated FFN (swiglu, ...) (#943)

Features

• Abstract asynchronous plotting executor (#1129) (f0743b7)
• Aggregate losses for temporal downscaler (#1069) (390ce34)
• Callbacks dependencies (#1128) (f791b75)
• Introduce mlp implementation for gated FFN (swiglu, ...) (#943) (2ed3417)

Bug Fixes

• Asyncio loop thread management with Python 3.13 (#1124) (7c9c8aa)
• models: Hierarchical model with multiple datasets (#1066) (987aa09)
• training: Gather sharded batches if loss does not support sharding (#1130) (921358c)

models: 0.16.0

0.16.0 (2026-05-22)

⚠ BREAKING CHANGES

• introduce mlp implementation for gated FFN (swiglu, ...) (#943)

Features

• Introduce mlp implementation for gated FFN (swiglu, ...) (#943) (2ed3417)

Bug Fixes

• Changed FFT2D low-pass filter from enabled to disabled by default (#1075) (336bacf)
• models: Gather_in_backward=False (#1138) (b732f6a)
• models: Hierarchical model with multiple datasets (#1066) (987aa09)

---

Important

Please do not change the PR title, manifest file, or any other automatically generated content in this PR unless you understand the implications. Changes here can break the release process.

⚠️ Merging this PR will:

• Create a new release
• Trigger deployment pipelines
• Update package versions

Before merging:

• Ensure all tests pass
• Review the changelog carefully
• Get required approvals

Release-please documentation