- in-kernel Neumann boundaries
- flag-interface for boundary handling makes one flag field multiple
  boundary handlings possible
- generator: support for bitwise logical operators

- splitted existing LBM boundary handling into two parts:
    -> generic part , that is used for FD as well and moved it to pystencils
    -> LBM specific part - remained in lbmpy

- bugfixes

- compute forces from pressure tensor instead of mu field

- collide-stream is the theoretically correct order - streamCollide
  optimization is not valid in all settings (e.g. when coupling to other
  methods)
- however, collide-stream is more expensive - since two sweeps have to be done

- systematic derivation of pressure tensor
- can be used alternatively to the chemical potential to obtain forces

- step class for LB phasefield generic enough to work with 3-phase and
  N-phase models
- cahn hilliard can either be solved by LBM or by finite differences
- 3 phase model can be solved with rho phase or without

- now an lbMethod or updateRule can be passed in directly
- made method/update rule/ast function independent i.e. no function
  uses the same parameters as on of the others

- 3 phase model works now with step sytem

- plotting
- calculation of force on boundary
- vtk outpu

- Step working for serial CPU scenarios

- scaling interface width eta instead of surface tensions tau to correct
  interface profile & surface tensions

- sphinx detection is not reliable, e.g. jupyter notebooks have sphinx
  imported at startup -> no caching from notebooks
- explicitly added cached functions via autofunction to docs
- some functions do not support memory cache, because memory cache can't
  handle non-hashable parameters -> introduced diskcacheNoFallback
  decorator for these functions

- single function to create kernel for specified target
- data type creation from string - reuse numpy functionality
- bugfixes in dot display