Skip to content

Issues: NVIDIA/numba-cuda

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

46 Open 18 Closed
46 Open 18 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

[FEA] Support launch bounds feature request New feature or request
#164 opened Mar 17, 2025 by ZzEeKkAa
[BUG]High Performance Cluster With Cuda 12.8 and Numba gives - CUDA_ERROR_UNSUPPORTED_PTX_VERSION and NVJITLINK_ERROR_PTX_COMPILE bug Something isn't working
#163 opened Mar 17, 2025 by julian2000P
8
[FEA] Provide an option to make LTO the default mode feature request New feature or request
#162 opened Mar 17, 2025 by gmarkall
[BUG] Compilation of function comparing two int32 inputs fails to compile with NvvmError exception bug Something isn't working
#157 opened Mar 13, 2025 by oleksandr-pavlyk
1
[MNT] Drop CUDA_USE_NVIDIA_BINDING and always use cuda.core (and fallback to cuda.bindings) feature request New feature or request
#154 opened Mar 10, 2025 by leofang
[FEA] Make cuda.core.utils.StridedMemoryView recognized by numba-cuda feature request New feature or request
#153 opened Mar 10, 2025 by leofang
1
[FEA] Make cuda.core.Buffer recognized by numba-cuda feature request New feature or request
#152 opened Mar 10, 2025 by leofang
[FEA] Make cuda.core.Stream recognized by numba-cuda by supporting the __cuda_stream__ protocol feature request New feature or request
#151 opened Mar 10, 2025 by leofang
[BUG] Add proper dependencies to conda package bug Something isn't working
#146 opened Mar 4, 2025 by vyasr
[Metadata] Eliminate duplicate metadata DIBasicType
#141 opened Feb 28, 2025 by jiel-nv
2
[FEA] Add support for alignment to cuda array helpers feature request New feature or request
#140 opened Feb 28, 2025 by tpn
1
[DOC] Consolidate docs for GPU-related environment variables doc Improvements or additions to documentation
#139 opened Feb 27, 2025 by leofang
[FEA]Support Custom Module Initialization Callbacks feature request New feature or request
#138 opened Feb 26, 2025 by isVoid
1
2
[FEA] Decompose Dim3s (x, y, z = cuda.blockDim) feature request New feature or request
#134 opened Feb 22, 2025 by brycelelbach
[MNT] Replace all internal Linker-related classes by cuda.core.(experimental).Linker
#129 opened Feb 20, 2025 by leofang
@brandon-b-miller
2
[RFC] Make cuda.core a required dependency
#128 opened Feb 20, 2025 by leofang
7 tasks
3
[FEA] Support PTX view in Devtools (e.g. NSight Compute) feature request New feature or request
#123 opened Feb 11, 2025 by gmarkall
[FEA] Supporting DLPacks feature request New feature or request
#122 opened Feb 7, 2025 by isVoid
2
[BUG] Problem linking cu code - with or without pynvjitlink bug Something isn't working
#119 opened Jan 31, 2025 by shaunc
1
[FEA] NVIDIA nvvm defaults to fma=1 and wish there was a way to tell it fma=0 feature request New feature or request
#118 opened Jan 28, 2025 by marioroy
[FEA] Make device attributes queryable feature request New feature or request
#111 opened Jan 17, 2025 by din14970
1
[FEA] Make block, thread, and warp indices unsigned feature request New feature or request
#109 opened Jan 9, 2025 by gmarkall
2
[BUG] test_empty_slice_1d/test_empty_slice_2d fail with NumPy 2.2.1 bug Something isn't working
#108 opened Jan 9, 2025 by leofang
[FEA] Support for caching kernels using NRT / add target context to kernels loaded from cache feature request New feature or request
#105 opened Jan 8, 2025 by gmarkall
[FEA] Support for Graph APIs feature request New feature or request
#102 opened Jan 2, 2025 by gmarkall
ProTip! Follow long discussions with comments:>50.