-
I wanted to make sure that it's thread-safe, e.g. OpenMP?
-
C. Elliott (2018): The simple essence of automatic differentiation. ICFP. ?
-
the explanation of the chunk size keyword does not make sense, it mentions `autojacvec=false`,
but `autojacvec=false` corresponds to `false: the Jacobian is constructed via FiniteDiff.jl`.
The `auto…
-
I am interested in the theory behind computation graph, but cannot find comprehensive material for it.
Can someone please share some key papers or lecture notes for computation graph?
-
Here is a MWE
```julia
using Enzyme
using FFTW
Enzyme.EnzymeRules.inactive(::typeof(FFTW.assert_applicable), args...) = nothing
function test(p, x)
p*x
return sum(abs2, x)
end
…
-
On my laptop it takes about 3 seconds to compile the reverse single variable example. Any ideas how to speed this up?
-
I'm running Enzyme 0.12.23, EnzymeCore 0.7.7, Linear Algebra 1.5.0, Sparse Arrays 1.10.0 in Julia 1.10.4 on a Windows machine. Without fail Enzyme crashes. I can get Zygote to differentiate the functi…
-
Currently, Enzyme.jl's reverse mode autodiff doesn't work correctly with Bumper.jl because if you give it a `Duplicated` buffer, it'll `+=` accumulate results into the duplicated buffer making the ans…
-
PR #51 introduces JAX sparse evaluation for models. Due to some limited functionality for the jax `BCOO` sparse array type, some work arounds were required to implement a few things. Subsequent releas…
-
I wanted to use split reverse mode in order to compute pullbacks with array outputs. The only doc I found is
so I tried it but it fails on Julia 1.11:
```julia
julia> using Enzyme
julia…