-
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…
-
**Describe the bug 🐞**
All the examples in the `SciMLSensitivity.jl` Documentation use a user-defined function for the ODEProblem. I need instead to define a parameter-dependent `SciMLOperator` (e.…
-
Enzyme doesn't seem to work with a broadcast and reduction on the GPU. Here is MWE
```julia
using Enzyme
using CUDA
f(x) = sum(abs2.(x))
x = CUDA.ones(64)
dx = zero(x)
autodiff(Reverse, f, Active,…
-
## Current Status
The [AD part](https://github.com/JuliaTrustworthyAI/CounterfactualExplanations.jl/blob/main/src/generators/gradient_based/loss.jl) of the package has not undergone any major overh…
-
In the notebooks on the documentation here:
https://jax.readthedocs.io/en/latest/notebooks/autodiff_cookbook.html
The author describes topics that he would like to showcase in a future Autodiff co…
-
Affected tests:
- `tests/autodiff/diff-ptr-type-array.slang`
Example output:
WGPU error: Error while parsing WGSL: :8:67 error: runtime-sized arrays can only be used in the address space…
-
After/with #589, I continued my hunt for differentiability with Enzyme a bit. With the transforms (more or less) differentiable, I found the first error from Enzyme at the spatial gradients, more prec…
-
I tried using static vectors for parameters, which works nicely. But not when combined with autodiff:
```julia
julia> using Optimization, OptimizationOptimJL, StaticArrays, ForwardDiff
# don't sp…
-
# Automatic differentiation from scratch | Emilio’s Blog
Automatic differentiation (AD) is one of the most important features present in modern frameworks such as Tensorflow, Pytorch, Theano, etc. AD…
-
Hello,
i have an issue with autodiff.py
could you help me please ?
Fred
ps : this is my first issue, i don't know very well the "bonnes pratiques"
All works expect the last line :
newtonSolv…