NVIDIA/cutlass

View on GitHub

CUDA Templates and Python DSLs for High-Performance Linear Algebra

Stars: 10.5k
Forks: 2.1k
Open beginner issues: 16
Indexed issues: 472
Avg merge: 3d 11h
Merged PRs (30d): 7

Dominant language: C++
License: No license data
Last GitHub push: Sep 17, 2026
Latest indexed: Sep 19, 2026
Contributing guide: No contributing guide
Code of conduct: No code of conduct
Beginner labels: help wanted good first issue

Beginner friendly Everything

Open All

34 beginner-friendly issues open

EllGemm ColumnMajor-output workspace sizing uses the unswapped problem shape and undersizes split-K semaphores Open

CUTLASS C++

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

NVIDIA/cutlass#3539 · 2 comments · Opened Aug 25, 2026
smem_atom_layoutSFB branches on majorSFA instead of majorSFB Open

CUTLASS C++

Difficulty 1/5 Under an hour Newbie friendliness 88/100

NVIDIA/cutlass#3535 · 3 comments · Opened Aug 25, 2026
rank_2k_universal and symm_universal Arguments constructors discard batch_stride_B Open

CUTLASS C++

Difficulty 2/5 1-3 hours Newbie friendliness 82/100

NVIDIA/cutlass#3532 · 3 comments · Opened Aug 25, 2026
Two small example bugs: wgrad split-k dumps the wrong tensor as Computed; FMHA diff-checker launches with block/grid swapped Open

CUTLASS C++

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

NVIDIA/cutlass#3525 · Opened Aug 24, 2026
Example 64 (Ada FP8 grouped GEMM) refuses capable GPUs via exact CC 8.9 gate Open

CUTLASS C++

Difficulty 1/5 Under an hour Newbie friendliness 91/100

NVIDIA/cutlass#3524 · 1 comment · Opened Aug 24, 2026
NonFusedGemmRun verification compares GEMM1 twice; GEMM0 output is never checked Open

CUTLASS C++

Difficulty 1/5 Under an hour Newbie friendliness 92/100

NVIDIA/cutlass#3523 · Opened Aug 24, 2026
TensorNHWC::inverse device path diverges from host path when strides are not w-multiples Open

CUTLASS C++

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

NVIDIA/cutlass#3519 · Opened Aug 24, 2026
TensorView::operator- does not compile; TensorViewPlanarComplex::reset ignores its size parameter Open

CUTLASS C++

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

NVIDIA/cutlass#3517 · Opened Aug 24, 2026
PredicateVector::is_zero ignores the last storage word when kBytes is a multiple of sizeof(Storage) Open

CUTLASS C++

Difficulty 2/5 1-3 hours Newbie friendliness 82/100

NVIDIA/cutlass#3512 · Opened Aug 24, 2026
LinearCombinationClamp with float output does not compile: platform numeric_limits<float> has no lowest() Open

CUTLASS C++

Difficulty 2/5 1-3 hours Newbie friendliness 82/100

NVIDIA/cutlass#3509 · 1 comment · Opened Aug 24, 2026
CuTeDSL: staged bool() with no arguments crashes the preprocessor with a raw IndexError Open

bug CuTe DSL

Difficulty 2/5 1-3 hours Newbie friendliness 82/100

NVIDIA/cutlass#3506 · 1 comment · 1 reaction · Opened Aug 24, 2026
Conv2d/Conv3d output-size constructors use R*dilation instead of the effective filter size ((R-1)*dilation+1) Open

CUTLASS C++

Difficulty 2/5 1-3 hours Newbie friendliness 82/100

NVIDIA/cutlass#3502 · Opened Aug 24, 2026
CuTeDSL: print_warning_once re-warns when more than one distinct message is used (lru_cache maxsize=1) Open

CuTe DSL

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

NVIDIA/cutlass#3501 · 1 comment · Opened Aug 24, 2026
CuTeDSL: nested comprehension breaks staged control flow later in the outer comprehension (NameError on the generator variable) Open

CuTe DSL

Difficulty 2/5 1-3 hours Newbie friendliness 86/100

NVIDIA/cutlass#3499 · Opened Aug 24, 2026
EpilogueDirectStore warp decomposition uses WarpShape::kN where WarpCount is meant Open

CUTLASS C++

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

NVIDIA/cutlass#3496 · Opened Aug 24, 2026
VisitorRowReduction::Callbacks::reduction is declared to return ElementCompute but has no return statement Open

CUTLASS C++

Difficulty 2/5 1-3 hours Newbie friendliness 75/100

NVIDIA/cutlass#3495 · 1 comment · Opened Aug 24, 2026
Sm90VisitorImplBase fixed-size specializations advance workspace by raw sizes while get_workspace_size/initialize_workspace round to 16 Open

CUTLASS C++

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

NVIDIA/cutlass#3494 · 1 comment · Opened Aug 24, 2026
numeric_limits< float_e2m3_t / float_e3m2_t >::lowest() returns a small negative value instead of the format minimum Open

CUTLASS C++

Difficulty 2/5 1-3 hours Newbie friendliness 88/100

NVIDIA/cutlass#3493 · Opened Aug 24, 2026
umul128 portable fallback computes an incorrect high product Open

CUTLASS C++

Difficulty 2/5 1-3 hours Newbie friendliness 82/100

NVIDIA/cutlass#3492 · Opened Aug 24, 2026
[BUG] Installed headers return CMake / configure_file placeholders for version numbers Open

? - Needs Triage bug CUTLASS C++ inactive-30d

Difficulty 2/5 1-3 hours Newbie friendliness 76/100

NVIDIA/cutlass#3472 · 1 comment · Opened Aug 17, 2026
[BUG] CuTe DSL TMEM allocator triggers internal struct.scalar pointer deprecation warnings Open

CuTe DSL

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

NVIDIA/cutlass#3451 · 1 comment · Opened Aug 12, 2026
[DOC] Broken notebook links Open

? - Needs Triage bug CuTe DSL documentation

Difficulty 2/5 1-3 hours Newbie friendliness 72/100

NVIDIA/cutlass#3414 · 3 comments · Opened Jul 28, 2026
[Feature] cute.compile hardcodes no_cache=True, disabling the DSL's content-addressed compile cache Open

Difficulty 2/5 1-3 hours Newbie friendliness 75/100

NVIDIA/cutlass#3398 · 3 comments · Opened Jul 20, 2026
[BUG] `CUTE_DSL_KEEP=sass` is ignored in cutlass-dsl 4.6.0 Open

? - Needs Triage bug CuTe DSL inactive-30d

Difficulty 2/5 1-3 hours Newbie friendliness 76/100

NVIDIA/cutlass#3365 · 3 comments · 1 reaction · Opened Jul 3, 2026
[BUG] cvt int8/uint8 -> bfloat16 emits a sm_90-only instruction on Ampere/Ada instead of the software fallback (arch gate too loose) Open

? - Needs Triage bug CuTe DSL inactive-30d

Difficulty 2/5 1-3 hours Newbie friendliness 78/100

NVIDIA/cutlass#3354 · 1 comment · Opened Jun 29, 2026
Stale comment in `examples/cute/tutorial/hopper/wgmma_sm90.cu` Open

? - Needs Triage CUTLASS C++ documentation inactive-30d

Difficulty 1/5 Under an hour Newbie friendliness 90/100

NVIDIA/cutlass#3340 · 4 comments · Opened Jun 22, 2026
[DOC] Wrong stride in Layout Algebra docs, composition worked example Open

? - Needs Triage documentation inactive-30d inactive-90d

Difficulty 1/5 Under an hour Newbie friendliness 92/100

NVIDIA/cutlass#3182 · 2 comments · Opened Apr 22, 2026
[Bug] `cutlass_profiler` fails to build with `CUTLASS_BUILD_SHARED_LIBS=OFF` Open

inactive-30d inactive-90d

Difficulty 2/5 1-3 hours Newbie friendliness 84/100

NVIDIA/cutlass#3179 · 3 comments · Opened Apr 21, 2026
[QST] Wrong comment of LayoutType::B128_BASE32B in make_umma_desc? Open

? - Needs Triage inactive-30d inactive-90d question

Difficulty 1/5 Under an hour Newbie friendliness 70/100

NVIDIA/cutlass#3089 · 2 comments · Opened Mar 6, 2026
[DOC] [CuTe DSL] Wrong output shape for logical_product? Open

? - Needs Triage documentation inactive-30d inactive-90d

Difficulty 2/5 1-3 hours Newbie friendliness 66/100

NVIDIA/cutlass#3085 · 4 comments · Opened Mar 1, 2026
[DOC] Empty code block in Fundamental Types -> Numeric Conversion Open

? - Needs Triage documentation inactive-30d

Difficulty 1/5 Under an hour Newbie friendliness 62/100

NVIDIA/cutlass#3064 · 3 comments · Opened Feb 24, 2026
[BUG] warning #2908-D: the implicit by-copy capture of "this" is deprecated Open

? - Needs Triage bug CUTLASS C++ inactive-90d

Difficulty 2/5 1-3 hours Newbie friendliness 68/100

NVIDIA/cutlass#2997 · 1 comment · Opened Feb 3, 2026
[BUG] example 06_splitK_gemm should allow post-Volta GPUs Open

? - Needs Triage bug inactive-30d inactive-90d

Difficulty 2/5 1-3 hours Newbie friendliness 65/100

NVIDIA/cutlass#1775 · 2 comments · Opened Sep 4, 2024
[DOC] Misleading comment in example 05_batched_gemm Open

? - Needs Triage documentation inactive-30d inactive-90d

Difficulty 1/5 Under an hour Newbie friendliness 65/100

NVIDIA/cutlass#1773 · 2 comments · Opened Sep 4, 2024

NVIDIA/cutlass

Get new issues in your inbox