-
Notifications
You must be signed in to change notification settings - Fork 820
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] GemmUniversal is slower than GemmSplitKParallel when M and N are small and K is large
? - Needs Triage
question
Question
#1586
opened Jun 12, 2024 by
ken012git
[QST] CUTLASS support for sparse matrix multiplication for X*W=Y with GPU sparse tensor core
? - Needs Triage
question
Question
#1585
opened Jun 12, 2024 by
YukeWang96
[QST] How to improve skinny matrix perf over Ampere like 3090?
#1582
opened Jun 11, 2024 by
leiwen83
[QST] Unknown CMake command "cutlass_example_add_executable"
? - Needs Triage
question
Question
#1581
opened Jun 10, 2024 by
soohyung-jang
[BUG] Circular Dependency in Header Files
? - Needs Triage
bug
Something isn't working
#1576
opened Jun 6, 2024 by
gavinchen430
[DOC] Incorrect link in main README file
? - Needs Triage
documentation
Documentation
#1575
opened Jun 5, 2024 by
gcunhase
[QST]What is the difference between Question
WmmaTensorOp
and TensorOp
?
? - Needs Triage
question
#1574
opened Jun 5, 2024 by
sleepwalker2017
Int8 multiplication with pytorch extension: namespace "torch" has no member "I8
? - Needs Triage
bug
Something isn't working
#1573
opened Jun 5, 2024 by
MuhammedHasan
[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
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
inactive-30d
question
#1532
opened May 10, 2024 by
HanGuo97
Previous Next
ProTip!
Follow long discussions with comments:>50.