## ContinuousNormalizingFlows v0.29.4 [Diff since v0.29.3](https://github.com/impICNF/ContinuousNormalizingFlows.jl/compare/v0.29.3...v0.29.4) **Merged pull requests:** - test without ode `sol_kwargs` (#503) (@prbzrg) **Closed issues:** - TagBot: Manual intervention needed for releases (#501)

## ContinuousNormalizingFlows v0.29.1 [Diff since v0.29.0](https://github.com/impICNF/ContinuousNormalizingFlows.jl/compare/v0.29.0...v0.29.1) **Merged pull requests:** - CompatHelper: bump compat for Optimization to 5, (keep existing compat) (#494) (@github-actions[bot])

## ContinuousNormalizingFlows v0.29.0 [Diff since v0.28.2](https://github.com/impICNF/ContinuousNormalizingFlows.jl/compare/v0.28.2...v0.29.0) ## Breaking changes - now `ICNFModel` gets `epochs` as `sol_kwargs` (to be able to use any optimizer) - now `ICNFModel` gets the batch size as `batchsize` instead of `batch_size` (to be similar to other packages naming) **Merged pull requests:** - Add Speed Tests (#486) (@prbzrg) - Update Usage (#487) (@prbzrg) - Handle Some Broken Tests (#488) (@prbzrg) - refactor jacobian parts (#490) (@prbzrg) - test more enzyme (#491) (@prbzrg) - Big Refactor (#492) (@prbzrg) - Add TrainMode with No Regularization (#493) (@prbzrg)

## ContinuousNormalizingFlows v0.28.1 [Diff since v0.28.0](https://github.com/impICNF/ContinuousNormalizingFlows.jl/compare/v0.28.0...v0.28.1) **Merged pull requests:** - test with sol_kwargs (#478) (@prbzrg) - add `ExplicitImports` (#481) (@prbzrg)

## ContinuousNormalizingFlows v0.28.0 [Diff since v0.27.0](https://github.com/impICNF/ContinuousNormalizingFlows.jl/compare/v0.27.0...v0.28.0) ## Breaking changes - `use_batch = false` replaced with `batch_size = 0` in MLJ models. - Augmented variables get regularized by default now. (only when n.augmented >= n.actual) - Return solve stats instead of printing them in MLJ models. **Merged pull requests:** - Test with `ForwardDiff` (#466) (@prbzrg) - CompatHelper: bump compat for ForwardDiff to 1 for package test, (keep existing compat) (#467) (@github-actions[bot]) - test default kwargs (#468) (@prbzrg) - CompatHelper: bump compat for JET to 0.10 for package test, (keep existing compat) (#469) (@github-actions[bot]) - Simplify Tests (#472) (@prbzrg) - CompatHelper: bump compat for DifferentiationInterface to 0.7, (keep existing compat) (#473) (@github-actions[bot]) - CompatHelper: bump compat for DifferentiationInterface to 0.7 for package test, (keep existing compat) (#474) (@github-actions[bot]) - CompatHelper: bump compat for DifferentiationInterface to 0.7 for package benchmark, (keep existing compat) (#475) (@github-actions[bot])

## ContinuousNormalizingFlows v0.26.1 [Diff since v0.26.0](https://github.com/impICNF/ContinuousNormalizingFlows.jl/compare/v0.26.0...v0.26.1) **Merged pull requests:** - CompatHelper: bump compat for Optimisers to 0.4, (keep existing compat) (#451) (@github-actions[bot]) - Bump codecov/codecov-action from 4 to 5 (#452) (@dependabot[bot]) - CompatHelper: bump compat for Zygote to 0.7, (keep existing compat) (#453) (@github-actions[bot]) - CompatHelper: bump compat for Zygote to 0.7 for package test, (keep existing compat) (#454) (@github-actions[bot]) - CompatHelper: bump compat for Zygote to 0.7 for package benchmark, (keep existing compat) (#455) (@github-actions[bot]) - Replace `Zygote` by `Enzyme` (#456) (@prbzrg) - rm CUDA & GPU test (#457) (@prbzrg) - test enzyme with reverse mode (#458) (@prbzrg) - back to zygote (#461) (@prbzrg) - add Lux compute types (#462) (@prbzrg)

## ContinuousNormalizingFlows v0.26.0 [Diff since v0.25.1](https://github.com/impICNF/ContinuousNormalizingFlows.jl/compare/v0.25.1...v0.26.0) **Merged pull requests:** - CompatHelper: bump compat for GPUArraysCore to 0.2 for package test, (keep existing compat) (#449) (@github-actions[bot])

## ContinuousNormalizingFlows v0.25.1 [Diff since v0.25.0](https://github.com/impICNF/ContinuousNormalizingFlows.jl/compare/v0.25.0...v0.25.1)