Skip to content

Pull requests: JuliaGPU/CUDA.jl

New pull request New
58 Open 1,565 Closed
58 Open 1,565 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
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Trial support for thread-block clusters cuda kernels Stuff about writing CUDA kernels. enhancement New feature or request needs changes Changes are needed. needs documentation Documentation is requested.
#2825 opened Jul 26, 2025 by kshyatt • Draft
1
Add a note suggesting users prefer PTX MMA over WMMA cuda kernels Stuff about writing CUDA kernels. documentation Improvements or additions to documentation performance How fast can we go?
#2816 opened Jul 23, 2025 by kshyatt Loading…
7
Benchmark GPUArrays AK reduction implementation
#2815 opened Jul 22, 2025 by christiangnrd Loading…
3
Use GPUArrays accumulation implementation cuda kernels Stuff about writing CUDA kernels.
#2813 opened Jul 20, 2025 by christiangnrd Loading…
1 task
2
Restore Enzyme to CI checks ci Everything related to continuous integration. needs changes Changes are needed.
#2807 opened Jul 1, 2025 by wsmoses Loading…
3
fix conversion of 0x0 CuSparseMatrixCSC <-> CSR bugfix This gets something working again. cuda libraries Stuff about CUDA library wrappers.
#2806 opened Jul 1, 2025 by tam724 Loading…
8
fixes the kron implementation for sparse + diagonal matrix
#2804 opened Jun 27, 2025 by tam724 Loading…
14
Expand eigen() and add eig[vals,vecs]() cuda libraries Stuff about CUDA library wrappers. enhancement New feature or request needs tests Tests are requested.
#2787 opened May 26, 2025 by matteosecli Loading…
16
add fastmath flag
#2732 opened Apr 9, 2025 by vchuravy • Draft
1
Added new api and fixed type errors in cuStateVec cuda libraries Stuff about CUDA library wrappers. enhancement New feature or request needs changes Changes are needed.
#2728 opened Mar 31, 2025 by LeeQY1996 • Draft
5
Use invariant.load for ldg
#2655 opened Feb 13, 2025 by vchuravy • Draft
1
1
Wrap and test some more Float16 intrinsics
#2644 opened Feb 6, 2025 by kshyatt Loading…
38
Try fast linear indexes for KA enhancement New feature or request needs changes Changes are needed. performance How fast can we go?
#2612 opened Jan 9, 2025 by vchuravy • Draft
8
Allow disabling the linking of libdevice in CUDACompilerParams enhancement New feature or request needs changes Changes are needed. speculative Not sure about this one yet.
#2611 opened Jan 8, 2025 by gbaraldi • Draft
7
make CUDA randn work with Zygote enhancement New feature or request needs changes Changes are needed.
#2581 opened Dec 9, 2024 by bgctw • Draft
5
Directed rounding cuda kernels Stuff about writing CUDA kernels. enhancement New feature or request needs tests Tests are requested.
#2576 opened Dec 3, 2024 by orkolorko • Draft
15
[CUSPARSE] Fix constructor of sparse empty matrices bugfix This gets something working again. cuda libraries Stuff about CUDA library wrappers.
#2575 opened Dec 2, 2024 by amontoison • Draft
1
WIP: Native I/O. cuda kernels Stuff about writing CUDA kernels. speculative Not sure about this one yet.
#2485 opened Sep 5, 2024 by maleadt • Draft
High Level Wrapper for Fused Matmul + Bias + Activation cuda libraries Stuff about CUDA library wrappers. enhancement New feature or request
#2360 opened May 4, 2024 by avik-pal • Draft
Mark more methods as device methods enhancement New feature or request
#2336 opened Apr 19, 2024 by vchuravy • Draft
4
Use PrecompileTools to warmup CUDA.jl enhancement New feature or request needs changes Changes are needed.
#2325 opened Apr 15, 2024 by vchuravy • Draft
5
Add a dispatch for LinearAlgebra.norm2 cuda array Stuff about CuArray. good first issue Good for newcomers needs changes Changes are needed.
#2302 opened Mar 22, 2024 by sharanry • Draft
1
3
Use TaskLocalValues enhancement New feature or request speculative Not sure about this one yet.
#2075 opened Sep 8, 2023 by vchuravy • Draft
1
Support FFT adjoint plans and test cuda libraries Stuff about CUDA library wrappers. enhancement New feature or request
#2073 opened Sep 4, 2023 by gaurav-arya • Draft
Add contract through FastmathOverlays.jl cuda kernels Stuff about writing CUDA kernels. enhancement New feature or request
#2037 opened Aug 16, 2023 by vchuravy • Draft
1
ProTip! Follow long discussions with comments:>50.