-
Notifications
You must be signed in to change notification settings - Fork 1k
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
[BUG] Where is 3.6.0 release?
? - Needs Triage
bug
Something isn't working
#2012
opened Dec 25, 2024 by
ankutalev
[BUG] [QST] Regression - why Sm90RowBroadcast in 3.5.1 stops support smem usage?
? - Needs Triage
bug
Something isn't working
#2010
opened Dec 23, 2024 by
ankutalev
[BUG] Removal of OpMultiplyAdd template substitutions from mma_sm80.h in 3.5.1
? - Needs Triage
bug
Something isn't working
#2009
opened Dec 23, 2024 by
ankutalev
[QST]How Does TMA Work in CUTLASS for Writing from Shared Memory to Global Memory?
? - Needs Triage
question
Question
#2008
opened Dec 23, 2024 by
ziyuhuang123
[QST] How to Let Question
__launch_bounds__ and setmaxnreg Work with Each Other?
? - Needs Triage
question
#2007
opened Dec 23, 2024 by
Maximilianxu
[BUG] wmma should be enabled w/ clang.
? - Needs Triage
bug
Something isn't working
#2006
opened Dec 20, 2024 by
Artem-B
[BUG] Unaligned access in test/unit/gemm/threadblock/batched_gemv.cu
? - Needs Triage
bug
Something isn't working
#2003
opened Dec 19, 2024 by
Artem-B
[QST]Behavior of TMA Store and Wait Mechanism in CUTLASS
? - Needs Triage
question
Question
#2002
opened Dec 19, 2024 by
ziyuhuang123
[QST] When to use MainloopSm90TmaGmmaWarpSpecializedFP8?
? - Needs Triage
question
Question
#2001
opened Dec 19, 2024 by
ginowu
[Proposal] layout deduction ambiguity of Nested Layout Access Problem
? - Needs Triage
bug
Something isn't working
#2000
opened Dec 18, 2024 by
yiakwy-xpu-ml-framework-team
[QST]Is the Key Difference Between mbarrier and barrier Their Handling of Producer-Consumer Count?
? - Needs Triage
question
Question
#1999
opened Dec 18, 2024 by
ziyuhuang123
[QST]How to Handle Synchronization with Different Thread Counts for Producer and Consumer in CUTLASS?
? - Needs Triage
question
Question
#1998
opened Dec 18, 2024 by
ziyuhuang123
[BUG] calling cast_smem_ptr_to_uint(device fn) from make_gmma_desc(host device fn) is not allowed
? - Needs Triage
bug
Something isn't working
#1997
opened Dec 18, 2024 by
lygztq
[QST] Gemm got 'incomplete type is not allowed' when use Sm90
? - Needs Triage
question
Question
#1996
opened Dec 18, 2024 by
TopIdiot
[QST] custom kernel integrated in Pytorch
? - Needs Triage
question
Question
#1991
opened Dec 16, 2024 by
IzanCatalan
[BUG] conv2d int8 doesn't work with python
? - Needs Triage
bug
Something isn't working
#1990
opened Dec 16, 2024 by
IzanCatalan
[QST] Global variable inside conv2d kernel
? - Needs Triage
question
Question
#1987
opened Dec 15, 2024 by
IzanCatalan
Unconstrained definition of
swap breaks types that pull in other namespaces with swap
#1984
opened Dec 12, 2024 by
miscco
[BUG] Funcionality TensorOp 80+ s8 * s8 + s32 => {s32, s8} not working
? - Needs Triage
bug
Something isn't working
#1981
opened Dec 11, 2024 by
IzanCatalan
[QST] Cutlass kernel causes no grad in torch backward pass
? - Needs Triage
question
Question
#1980
opened Dec 10, 2024 by
MinghaoYan
[QST] Integer Data Types are available for Conv2d fprop?
? - Needs Triage
question
Question
#1979
opened Dec 10, 2024 by
IzanCatalan
[QST] What Conv2d definition is used with Python and Pytorch
? - Needs Triage
question
Question
#1978
opened Dec 10, 2024 by
IzanCatalan
[QST] Where is exactly the definiton code of fprop convolution?
? - Needs Triage
question
Question
#1976
opened Dec 9, 2024 by
IzanCatalan
[FEA]Is it support BlackWell Architecture
feature request
New feature or request
#1975
opened Dec 9, 2024 by
Emiyagzm
Previous Next
ProTip!
Find all open issues with in progress development work with linked:pr.