|
What is the correct way to autodiff a simple CUDA kernel using Reactant.jl and Enzyme.jl
|
|
20
|
551
|
September 23, 2025
|
|
SciMLSensitivity fails on GPU?
|
|
5
|
127
|
September 22, 2025
|
|
Make Lux.jl/Zygote.jl choose gradient type based on the superset of the weight type
|
|
0
|
68
|
September 17, 2025
|
|
`apply` do not work anymore with StatefulLuxLayer (by Luxv1.19)
|
|
5
|
203
|
September 16, 2025
|
|
NamedTuple from the ComponentArray
|
|
3
|
210
|
September 11, 2025
|
|
Sequence language models in Julia
|
|
6
|
525
|
August 18, 2025
|
|
I heard lux.jl is moving to reactant.jl. Where can I help?
|
|
4
|
449
|
August 15, 2025
|
|
Is it possible to evaluate the objective function within the "Optimisers.apply!" function?
|
|
2
|
95
|
August 6, 2025
|
|
Loading Lux params and states in a new script
|
|
1
|
120
|
August 5, 2025
|
|
How to use Lux.apply for a composite model
|
|
1
|
117
|
August 5, 2025
|
|
Using Enzyme.jl with Flux: Issues Computing Gradients of a Model with Duplicated Parameters and Mixed Forward/Reverse AD
|
|
11
|
412
|
July 29, 2025
|
|
Just-in-time gradient optimization idea
|
|
2
|
237
|
July 29, 2025
|
|
Accepted mask type for Augmentor.jl
|
|
0
|
64
|
July 28, 2025
|
|
Enzyme throws `alwaysinline mustprogress` when using GraphNeuralNetworks to mutate Graphs
|
|
6
|
209
|
July 15, 2025
|
|
NeuralPDE on GPU throws NaNs when I use a source term elevated to some power
|
|
2
|
266
|
July 6, 2025
|
|
How to use Lux's `apply` function?
|
|
2
|
195
|
June 30, 2025
|
|
Custom differentiation with Flux
|
|
2
|
110
|
June 26, 2025
|
|
Training Neural ODEs - Advice
|
|
2
|
194
|
June 24, 2025
|
|
A custom type-stable regularization function in Lux & Enzyme
|
|
0
|
119
|
June 18, 2025
|
|
Loading resampled data for PINN in Reactant + Enzyme + Lux
|
|
2
|
180
|
June 17, 2025
|
|
Issue with backprop in a custom recurrent `Lux` layer
|
|
6
|
222
|
June 16, 2025
|
|
Weird behavior of GraphNeuralNetworks.jl `SGConv` layer within `Flux.withgradient`
|
|
5
|
227
|
June 14, 2025
|
|
Native Julia FID (Fréchet Inception Distance) Computation
|
|
0
|
106
|
June 11, 2025
|
|
Type stability of `Lux.batched_jacobian`
|
|
5
|
174
|
June 10, 2025
|
|
Build a Build deep neural network classifier using a long short-term memory (LSTM) architecture
|
|
3
|
175
|
June 4, 2025
|
|
[Resolved] ERROR: SciMLSensitivity
|
|
7
|
220
|
June 3, 2025
|
|
Questions about the DiffEqFlux multiple shooting example
|
|
4
|
185
|
June 2, 2025
|
|
Facing high loss values when training the SciML model
|
|
1
|
118
|
May 29, 2025
|
|
Training a Neural ODE system using the output of a Method-Of-Lines computation
|
|
2
|
176
|
May 26, 2025
|
|
Lack of conexionist NN package?
|
|
1
|
151
|
May 25, 2025
|