Skip to content

Issues: NVIDIA/cutlass

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

215 Open 1,039 Closed
215 Open 1,039 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

[QST] Question about example 69 ? - Needs Triage question Question
#2096 opened Feb 10, 2025 by ZZBoom
[BUG] Tmem tiled copy with non power-of-2 size fails to compile ? - Needs Triage bug Something isn't working
#2094 opened Feb 10, 2025 by tridao
3
[QST]Inquiry About the Computation Size in a Single cute::gemm Call in CUTLASS ? - Needs Triage question Question
#2092 opened Feb 8, 2025 by ziyuhuang123
[DOC] Possible typos in fundamental_types.md document ? - Needs Triage documentation Documentation
#2091 opened Feb 8, 2025 by jc19chaoj
[QST] how to use groupwise scaling along M for FP8 gemm to impelement per-token-per-128-channel and blockwise? ? - Needs Triage question Question
#2087 opened Feb 7, 2025 by yizhang2077
4
[BUG] ConvOperation3x has two extended_name methods? ? - Needs Triage bug Something isn't working
#2085 opened Feb 7, 2025 by henrylhtsang
About the make_tensor function
#2084 opened Feb 6, 2025 by LANSHANGH
[BUG] CuTE: inconsitent results when using a dynamically vs statically shaped tiler in local_tile ? - Needs Triage bug Something isn't working
#2083 opened Feb 6, 2025 by joshgev
1
[BUG] Copy constructor of tma descriptor produces a corrupted copy ? - Needs Triage bug Something isn't working
#2081 opened Feb 5, 2025 by pavlo-hilei
1
[QST] Adding a flag in Tensor Ref Class ? - Needs Triage question Question
#2080 opened Feb 5, 2025 by IzanCatalan
4
[BUG] undefined symbol: cudaGetDriverEntryPointByVersion ? - Needs Triage bug Something isn't working
#2079 opened Feb 5, 2025 by danthe3rd
1
2
[QST] Getting a template error trying to use cutlass's depthwise 2D convolution with pytorch ? - Needs Triage question Question
#2077 opened Feb 4, 2025 by ahmadsharif1
3
[QST] Quantization from fp32 to nvf4? ? - Needs Triage question Question
#2076 opened Feb 3, 2025 by tsengalb99
1
[QST] How to apply StreamK to hopper warp specialized GEMM ? - Needs Triage question Question
#2075 opened Feb 3, 2025 by Hongbosherlock
6
[QST]Question About the Use of MMA In-Flight in SS_WarpSpecialized ? - Needs Triage question Question
#2074 opened Feb 3, 2025 by ziyuhuang123
1
[FEA] Complete the cutlass::library::GemmDescription class to cover Hopper GEMM kernels ? - Needs Triage feature request New feature or request
#2073 opened Jan 30, 2025 by manishucsd
3
[QST] Build for sm100 Blackwell GPUs ? - Needs Triage question Question
#2072 opened Jan 30, 2025 by phantaurus
4
[BUG] Mixed Precision Gemm Correctness Regression in Cutlass 3.7/3.8 ? - Needs Triage bug Something isn't working
#2070 opened Jan 29, 2025 by jwfromm
4
[QST] How to implement a fused mixed precision matrix multiplication such as w4a4 + w16a16? ? - Needs Triage question Question
#2058 opened Jan 24, 2025 by hyx1999
2
[QST]Why Does CUTLASS Handle the First K Dimension Separately in Matrix Multiplication? ? - Needs Triage question Question
#2055 opened Jan 23, 2025 by ziyuhuang123
1
[QST] in implicit gemm conv, why does not support split-k when group !=1 ? ? - Needs Triage question Question
#2049 opened Jan 21, 2025 by preFiredman
3
[QST] Terminology question on GMMA::ScaleOut::One ? - Needs Triage question Question
#2046 opened Jan 17, 2025 by haeunlee99
3
[BUG][QST] Hopper Grouped GEMM Fails When Workspace not aligned at 64, but MinWorkspaceAlignment =16 ? - Needs Triage bug Something isn't working
#2042 opened Jan 16, 2025 by ankutalev
5
[BUG] Modifying the block/warptile shapes and the output datatype in the unit test causes the tests to fail. ? - Needs Triage bug Something isn't working
#2041 opened Jan 16, 2025 by xiaonans
1
[QST] link invalid in efficient_gemm.md ? - Needs Triage question Question
#2038 opened Jan 13, 2025 by unship
1
ProTip! Follow long discussions with comments:>50.