Skip to content

Issues: FluxML/NNlib.jl

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

82 Open 133 Closed
82 Open 133 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

Update lineplot syntax in activations.jl docs to work with new UnicodePlots.jl
#623 opened Jan 8, 2025 by zengmao
batched_mul launches one kernel per matrix when eltypes differ rather than promoting
#621 opened Jan 7, 2025 by THargreaves
2
Test failures with Zygote 0.7
#619 opened Jan 5, 2025 by mcabbott
1
maxpool/meanpool doesn't support Complex CuArrays
#610 opened Oct 22, 2024 by avik-pal
Exported symbol σ too generic breaking
#604 opened Sep 15, 2024 by nomadbl
2
batched_transpose with multiple batch dimensions
#588 opened May 27, 2024 by AntonOresten
3
[AMDGPU] Reconsider MIOpen softmax once it is fixed
#586 opened May 19, 2024 by pxl-th
1
batched_mul doesn't work with MtlArrays
#581 opened May 11, 2024 by forrestlaine
1
1
NaN with custom mask for MultiHeadAttention
#572 opened Apr 3, 2024 by mashu
3
Add QuickGELU (lookup-table based)
#561 opened Jan 22, 2024 by PallHaraldsson
1
Incorrect gradients of batchnorm in testmode bug CUDA help wanted
#548 opened Oct 27, 2023 by phaim
3
NNlib.gather triggers InvalidIRError when doing Forward over Reverse for hessian computation on GPU CUDA help wanted
#547 opened Oct 26, 2023 by vpuri3
4
How to NNlib.conv documentation help wanted
#544 opened Oct 19, 2023 by MariusDrulea
error for scatter with Metal arrays
#534 opened Sep 19, 2023 by CarloLucibello
8
move tests to ReTestItems
#533 opened Sep 11, 2023 by CarloLucibello
batched_mul! doesn't support arrays of dimension larger than 3
#529 opened Aug 31, 2023 by ZhaoFancy
1
I want to implement some activation functions, e.g. NLReLU and ALReLU, maybe even combine (and CReLU?) enhancement
#528 opened Aug 11, 2023 by PallHaraldsson
1
Add warnings/errors on CPU kernels when called with GPU arrays good first issue
#523 opened Jul 26, 2023 by ToucheSir
1
Type instabilities lead to insane number of CPU allocations on grouped convolutions performance
#520 opened Jul 5, 2023 by mashu
2
Inplace version of batched adjoint/transpose good first issue
#502 opened Jun 24, 2023 by chengchingwen
7
remove Requires in favor of extensions
#494 opened Jun 11, 2023 by CarloLucibello
2 tasks
spconv ... sparse convolution enhancement help wanted
#493 opened Jun 6, 2023 by dorn-gerhard
1
type-piracy of materialize CUDA good first issue
#504 opened Apr 18, 2023 by vtjnash
1
Migrate to KernelAbstractions.jl for handwritten kernels help wanted
#479 opened Mar 1, 2023 by pxl-th
10
warn on batched_mul_generic!? performance
#478 opened Feb 25, 2023 by chengchingwen
1
2
ProTip! Exclude everything labeled bug with -label:bug.