|
My journey training an LLM from scratch in Julia (and why I see huge potential)
|
|
5
|
525
|
April 24, 2026
|
|
Why is Flux/NNlib falling back to im2col instead of MIOpen on AMD GPU?
|
|
3
|
152
|
March 10, 2026
|
|
Multi-GPU inference in Flux.jl
|
|
2
|
129
|
January 24, 2026
|
|
Identical input in Zygote leads to different outputs
|
|
1
|
135
|
January 19, 2026
|
|
Reset model parameters Flux.jl
|
|
3
|
1999
|
January 15, 2026
|
|
CUDA Warning about freeing DeviceMemory
|
|
1
|
66
|
January 15, 2026
|
|
Machine Learning and Deep Learning Course with Julia
|
|
1
|
256
|
January 5, 2026
|
|
Flux newbie: simple Markov
|
|
5
|
318
|
December 3, 2025
|
|
Using `CartesianIndex` with Flux.jl
|
|
3
|
71
|
December 3, 2025
|
|
DiffOpt / JuMP: zero gradient for variable fixed by equality constraint
|
|
12
|
328
|
November 28, 2025
|
|
Issue: Enzyme + Flux double differentiation on custom layer
|
|
3
|
154
|
October 30, 2025
|
|
Best options for Graph Neural Network integration with Flux
|
|
5
|
211
|
October 24, 2025
|
|
Fitting neural ODE to periodic time series
|
|
18
|
5076
|
October 13, 2025
|
|
Wrapping a Flux FCN model with MLJFlux
|
|
0
|
35
|
September 1, 2025
|
|
Is it possible to evaluate the objective function within the "Optimisers.apply!" function?
|
|
2
|
87
|
August 6, 2025
|
|
Using Enzyme.jl with Flux: Issues Computing Gradients of a Model with Duplicated Parameters and Mixed Forward/Reverse AD
|
|
11
|
366
|
July 29, 2025
|
|
Why is the loss function increasing when fitting a line?
|
|
2
|
152
|
July 10, 2025
|
|
PReLU with long compilation time
|
|
1
|
118
|
June 12, 2025
|
|
[pre-ANN] Differentiable FDTD for inverse design in photonics, acoustics and RF
|
|
54
|
5176
|
May 10, 2025
|
|
Warning: Package cuDNN not found in current path
|
|
5
|
1103
|
May 8, 2025
|
|
.== and .<= inside Zygote.gradient() are inaccurate on GPU
|
|
10
|
284
|
April 30, 2025
|
|
Memory usage increasing with each epoch
|
|
18
|
970
|
April 14, 2025
|
|
Improve performance in Flux.jl
|
|
0
|
101
|
April 10, 2025
|
|
GPU backend-agnostic way to create efficiently random number on the GPU
|
|
3
|
178
|
March 3, 2025
|
|
Distributed Data Parallel training with 2 GPUs fails with Flux.jl on AMD GPUs
|
|
7
|
189
|
February 18, 2025
|
|
Save model when training with Distributed Data Parallel
|
|
0
|
87
|
February 11, 2025
|
|
Segfault using Flux + Intel integrated GPU
|
|
2
|
156
|
February 6, 2025
|
|
Help with CUDA and Flux. DeviceMemory issue
|
|
2
|
162
|
February 2, 2025
|
|
Gradient not being computed when training NN using Flux
|
|
3
|
157
|
January 30, 2025
|
|
Announcing TinyMachines.jl
|
|
0
|
369
|
January 17, 2025
|