-
Notifications
You must be signed in to change notification settings - Fork 1.2k
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.
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
Author
Label
Projects
Milestones
Assignee
Sort
Issues list
[QST] Will cutlass add MLA implementation for non Blackwell?
#2264
opened Apr 25, 2025 by
ghostplant
[QST] How to use Grouped_gemm when MNK is not a regular shape
? - Needs Triage
question
Question
#2263
opened Apr 25, 2025 by
chenhongyu2048
[FEA] Has CUTLASS considered supporting Zero-points and block-wise scaling in Hoppr Mixed Grouped Gemm recently?
? - Needs Triage
feature request
New feature or request
#2261
opened Apr 24, 2025 by
mengsoso
[QST] Why only N={64, 128, 192, 256} is supported for mxf8f6f4 GeMM?
? - Needs Triage
question
Question
#2260
opened Apr 24, 2025 by
Algy
[QST] When do we use Question
as_position_independent_swizzle_tensor()
?
? - Needs Triage
question
#2259
opened Apr 24, 2025 by
flytigerw
[QST]How to write column major output epilogue in cutlass2.x
? - Needs Triage
question
Question
#2258
opened Apr 23, 2025 by
tlogn
[FEA] CVT F32 -> TF32 PTX for sm80
? - Needs Triage
feature request
New feature or request
#2254
opened Apr 19, 2025 by
osayamenja
[BUG] Compile warning/error - Something isn't working
-Werror=unused-but-set-variable
unused curr_stride in cute/layout.hpp via flash attention.
? - Needs Triage
bug
#2253
opened Apr 19, 2025 by
Skylion007
[QST] how to use vectorized copy when size is not perfectly aligned?
? - Needs Triage
question
Question
#2252
opened Apr 19, 2025 by
botbw
[QST] whats the difference between OpMultiplyAddFastAccum and OpMultiplyAdd tag?
? - Needs Triage
question
Question
#2246
opened Apr 17, 2025 by
danielhua23
[FEA][torchinductor-EVT] tensor construction API that takes in shape + stride directly
? - Needs Triage
feature request
New feature or request
#2245
opened Apr 17, 2025 by
mlazos
[FEA][torchinductor-EVT] Allow function source code to be passed directly to EVT tracer
? - Needs Triage
feature request
New feature or request
#2244
opened Apr 17, 2025 by
mlazos
[BUG][torchinductor-EVT] cutlass/python/cutlass has extra dependencies that aren't needed for EVT
? - Needs Triage
bug
Something isn't working
#2243
opened Apr 16, 2025 by
mlazos
[QST][CUTE] How to systematically and easily compose the cute layout algebra operations to get custom layout
? - Needs Triage
question
Question
#2241
opened Apr 16, 2025 by
danielhua23
[QST] why use AutoVectoringCopy rather LDSM in hopper mixed gemm?
? - Needs Triage
question
Question
#2239
opened Apr 13, 2025 by
danielhua23
[FEA] Blackwell support for python libraries.
? - Needs Triage
feature request
New feature or request
#2237
opened Apr 12, 2025 by
eliphatfs
[QST]Do we need to tune cutlass gemm to use it for all shape?
? - Needs Triage
question
Question
#2235
opened Apr 11, 2025 by
sleepwalker2017
[QST] How does make_tiled_copy_A determine the source address for copying?
? - Needs Triage
question
Question
#2232
opened Apr 10, 2025 by
ezioliao
[BUG] No TMEM allocation in Blackwell CuTe tutorial examples
? - Needs Triage
bug
Something isn't working
#2230
opened Apr 8, 2025 by
allispaul
[QST] What's the difference between make_fragment_like and make_tensor_like?
? - Needs Triage
question
Question
#2228
opened Apr 7, 2025 by
iryanin
[DOC] all images in cutlass/media/docs/cpp/cute cannot display
? - Needs Triage
documentation
Documentation
#2227
opened Apr 7, 2025 by
hlyix
[DOC]构建 cutlass_profiler
? - Needs Triage
documentation
Documentation
#2226
opened Apr 7, 2025 by
ll000x
[FEA]examples/cute/tutorial/tiled_copy.cu parameterization?
? - Needs Triage
feature request
New feature or request
#2225
opened Apr 6, 2025 by
ziyuhuang123
[BUG] Blackwell MLA perf for split-k
? - Needs Triage
bug
Something isn't working
#2222
opened Apr 4, 2025 by
divchenko
[QST] How to pack int4 tensor correctly in PyTorch
? - Needs Triage
question
Question
#2218
opened Apr 3, 2025 by
yicwang
Previous Next
ProTip!
Updated in the last three days: updated:>2025-04-22.