-
Notifications
You must be signed in to change notification settings - Fork 817
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] Is there grouped_gemv
? - Needs Triage
question
Question
#1572
opened Jun 4, 2024 by
hanzz2007
[BUG] Failing to build on MSVC due to call to _div128
? - Needs Triage
bug
Something isn't working
#1571
opened Jun 3, 2024 by
drisspg
How to perform operations like crop, concat on tensors in CuTe? [QST]
? - Needs Triage
question
Question
#1570
opened Jun 3, 2024 by
Ricky-KLA
[FEA] Add cuTensorMapEncodeTiled to CudaHostAdapter
? - Needs Triage
feature request
New feature or request
#1566
opened May 31, 2024 by
drisspg
[QST] GEMM Epilogue Fusion: Row-wise and Column-wise Multiplication
? - Needs Triage
question
Question
#1565
opened May 31, 2024 by
Hongbosherlock
[QST]Why fp8 convert only has float2fp8 function without ptx ?
? - Needs Triage
question
Question
#1564
opened May 31, 2024 by
WtDMaO
[QST] GEMM Epilogue Fusion: Element-wise Ops and Two-Tensor Element-wise Multiplication
? - Needs Triage
question
Question
#1563
opened May 30, 2024 by
HanGuo97
[QST] (BUG?)The stride of TensorNCxHWx seems to be confusing when C is smaller than Interleave
? - Needs Triage
question
Question
#1562
opened May 30, 2024 by
gujiewen
Tiled copy misaligned, how to solve it?
? - Needs Triage
question
Question
#1561
opened May 30, 2024 by
4grass
Warp Group MMA vs Warp MMA
? - Needs Triage
question
Question
#1560
opened May 30, 2024 by
OrenLeung
[QST/BUG] why cute kernel transfers so much data between L2 and gmen than cublas kernel
? - Needs Triage
question
Question
#1556
opened May 29, 2024 by
irasin
[QST]How to implement different type between D0(D1) and D2 based on 45_dual_gemm example
? - Needs Triage
question
Question
#1555
opened May 29, 2024 by
Sunny-bot1
[QST] The best way to do D = func(A x B) x C.
? - Needs Triage
question
Question
#1551
opened May 27, 2024 by
amazingyyc
[QST] Hopper mixed precision gemm always worse than FP8
? - Needs Triage
question
Question
#1549
opened May 24, 2024 by
divchenko
[BUG] Cutlass Python API silently fails in (suspected) unsupported case
? - Needs Triage
bug
Something isn't working
#1547
opened May 23, 2024 by
LucasWilkinson
[QST] Row major for int8 matrix multiplications?
? - Needs Triage
question
Question
#1533
opened May 10, 2024 by
ken012git
[QST] Question
cutlass::Array
and cute::Tensor
--- using CUTLASS utility structs/classes with CUTE (such as NumericArrayConverter
)
? - Needs Triage
question
#1532
opened May 10, 2024 by
HanGuo97
[QST/BUG] Should shared memory usage be checked for multistage pipeline?
? - Needs Triage
question
Question
#1525
opened May 7, 2024 by
wzhcz8902
[BUG] Composition between Something isn't working
inactive-30d
Tensor
and Layout
as shown in 03_tensor.md
does not compile
? - Needs Triage
bug
#1519
opened Apr 30, 2024 by
armbuster
[QST] Epilogue Reduction
? - Needs Triage
inactive-30d
question
Question
#1518
opened Apr 30, 2024 by
jeromeku
[QST] use FastLinearCombinationClamp to convert half accumulator to int8_t output?
? - Needs Triage
inactive-30d
question
Question
#1516
opened Apr 30, 2024 by
ken012git
Previous Next
ProTip!
Updated in the last three days: updated:>2024-06-01.