.== and .<= inside Zygote.gradient() are inaccurate on GPU
|
|
10
|
161
|
April 30, 2025
|
Memory usage increasing with each epoch
|
|
18
|
627
|
April 14, 2025
|
Improve performance in Flux.jl
|
|
0
|
51
|
April 10, 2025
|
Warning: Package cuDNN not found in current path
|
|
4
|
905
|
April 2, 2025
|
GPU backend-agnostic way to create efficiently random number on the GPU
|
|
3
|
108
|
March 3, 2025
|
Distributed Data Parallel training with 2 GPUs fails with Flux.jl on AMD GPUs
|
|
7
|
99
|
February 18, 2025
|
Save model when training with Distributed Data Parallel
|
|
0
|
43
|
February 11, 2025
|
Segfault using Flux + Intel integrated GPU
|
|
2
|
71
|
February 6, 2025
|
Help with CUDA and Flux. DeviceMemory issue
|
|
2
|
75
|
February 2, 2025
|
Gradient not being computed when training NN using Flux
|
|
3
|
90
|
January 30, 2025
|
Announcing TinyMachines.jl
|
|
0
|
342
|
January 17, 2025
|
Extremely high memory consumption on CPU
|
|
2
|
112
|
January 13, 2025
|
How to compute TanhExp / TeLU function accurately?
|
|
10
|
166
|
January 6, 2025
|
[pre-ANN] Differentiable FDTD for inverse design in photonics, acoustics and RF
|
|
53
|
4342
|
December 20, 2024
|
[ANN] Jello.jl - Manufacturable geometry generation for topology optimization & generative design
|
|
14
|
1771
|
December 19, 2024
|
How to implement a sparse decoder layer in Flux.jl?
|
|
1
|
78
|
December 17, 2024
|
"gpu_device" not defined in DDP with Flux
|
|
2
|
56
|
December 15, 2024
|
Cannot differentiate through a multivariate log normal probability density with Zygote
|
|
4
|
138
|
December 11, 2024
|
Flux and Metal circular dependencies in 1.10.7
|
|
2
|
101
|
December 11, 2024
|
Basic example for using Transformers.jl for sequential autoencoding
|
|
0
|
50
|
December 10, 2024
|
Sparse loss with Flux
|
|
3
|
83
|
December 9, 2024
|
AD Troubles in Flux and Unusual Loss
|
|
1
|
106
|
November 24, 2024
|
Downloading transformer weights
|
|
0
|
41
|
November 21, 2024
|
Kernel methods inside of Flux
|
|
1
|
112
|
November 20, 2024
|
Flux conv with GPU Arrays
|
|
5
|
114
|
November 12, 2024
|
Avoid allocation of a Flux model on the CPU
|
|
3
|
116
|
October 27, 2024
|
Custom Flux.jl Layer Not Updating (problem with Flux.trainable?)
|
|
2
|
211
|
October 19, 2024
|
How to create Dense with initialed weights in vector
|
|
0
|
31
|
October 14, 2024
|
Flux - sigmoid in last layer destroys learning?
|
|
13
|
194
|
October 11, 2024
|
Flux has no Lecun Normalization weight init function?
|
|
0
|
80
|
October 9, 2024
|