-
```julia
using Enzyme, Reactant
f(x) = sum(abs2, x .* x)
function enzyme_split_mode(x)
dx = Enzyme.make_zero(x)
forward, reverse = autodiff_thunk(
ReverseSplitWithPrimal, Const{typeo…
-
I diagnosed this problem with DifferentiationInterface, but it also appears using Enzyme's own `hvp` function.
The following code is run on Julia 1.11 with Enzyme v0.13.14. On Julia 1.10 it returns th…
-
Hello, I wonder if Reactant works with Conv layers, it seems it works in forward but not in the gradient pass, neither on cpu of gpu
version :
```
Julia Version 1.10.6
Commit 67dffc4a8ae (2024-10-28…
-
Hi,
the following is veeeery slow on CUDA and also errors out:
```julia
julia> using CUDA, Enzyme, RadonKA, DifferentiationInterface
julia> function main()
arr = Array(rand(Float3…
-
CC @mofeing
I get an error when trying to compile a gradient of a function that accepts complex parameters.
```julia
julia> using Enzyme
julia> using Reactant
AssertionError("Could not find registe…
-
I am trying to make the RHS of an ODEProblem Enzyme compatible. My function has the signature `(du, u, p, t)` and I try to differentiate `du` for `u` for constant `p` and `t`. I hit the error
```
ERRO…
-
output of `rustc +enzyme --version --verbose`:
rustc 1.84.0-nightly (1203575c6 2024-10-30)
binary: rustc
commit-hash: 1203575c627a2e96bc3543145526b5091a58be65
commit-date: 2024-10-30
host: x86_64-unk…
-
I am on Enzyme main (b63f36f6) and Julia 1.10.6. The following used to work.
```julia
using Enzyme
f_nest(x) = 2 * x^4
deriv(f, x) = first(first(autodiff(Reverse, f, Active(x))))
f′(x) = deriv(f_nest,…
-
```julia
using Enzyme, Lux, SimpleChains, Random
model = Chain(Dense(10, 10, tanh), Dense(10, 10, tanh))
scmodel = ToSimpleChainsAdaptor(static((10,)))(model)
x = rand(Float32, 10, 2)
ps, st …
-
@wsmoses Opening an issue for the GC error I see, I added you to the repo where my code is, it's a private one in the DJ4Earth repository. Running `julia --project=. technical_paper.jl` should reprod…