# Julia calling Stan C++ directly

**URL:** <https://discourse.julialang.org/t/julia-calling-stan-c-directly/23212>\
**Category:** Tooling\
**Created:** [April 16, 2019, 4:44pm UTC](https://discourse.julialang.org/t/julia-calling-stan-c-directly/23212 "2019-04-16T16:44:29Z")\
**Posts on this page:** 1\
**Page:** 2

<div class="post-metadata">

**Author:** ![chakravala](https://sea2.discourse-cdn.com/julialang/user_avatar/discourse.julialang.org/chakravala/32/6832_2.png) [@chakravala](https://discourse.julialang.org/u/chakravala)\
**Post date:** [April 21, 2019, 2:49am UTC](https://discourse.julialang.org/t/julia-calling-stan-c-directly/23212/21 "2019-04-21T02:49:08Z")

</div>

> [@Elrod](#):
>
> @chakravala Will it also do reverse auto diff, or create symbolic expressions via `Reduce` ?

Support for that will be implemented later, but an option for both forward and reverse mode is already being built into the underlying `VectorSpace` structure with [DirectSum.jl](https://github.com/chakravala/DirectSum.jl) which is used in `Grassmann`. The forward and reverse mode differentiation is going to be build into the tangent vector space, and then this information can be used to specialize the dispatch for methods. I don’t know yet how the reverse mode features will be implemented yet, but have planned ahead for expanding the dispatch.

[Previous page](https://discourse.julialang.org/t/julia-calling-stan-c-directly/23212.md?page=1)