refactor: use layers from `Boltz`

SciML / DiffEqFlux.jl

Pre-built implicit layer architectures with O(1) backprop, GPUs, and stiff+non-stiff DE solvers, demonstrating scientific machine learning (SciML) and physics-informed machine learning methods

https://docs.sciml.ai/DiffEqFlux/stable

MIT License

871 stars 157 forks source link

refactor: use layers from `Boltz` #937

Closed avik-pal closed 2 months ago

avik-pal commented 2 months ago

fixes #929

needs https://github.com/LuxDL/Boltz.jl/pull/54

avik-pal commented 2 months ago

Let's merge this once the CI passes. Doing the Lux 1.0 update here would bloat the PR too much