-
Notifications
You must be signed in to change notification settings - Fork 1.9k
Pull requests: NVIDIA/cutlass
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
Enable strict C++ compiler warnings with -Werror
inactive-30d
#3123
opened Mar 22, 2026 by
maxwbuckley
Loading…
3 of 4 tasks
[bugfix] use acquire to prevent reordering.
inactive-30d
#3118
opened Mar 20, 2026 by
shubaoyu2
Contributor
Loading…
[FMHA] Add SM110 support for Blackwell FMHA example (77_blackwell_fmha)
inactive-30d
#3112
opened Mar 18, 2026 by
LiangSu8899
Loading…
fix(CuTeDSL): correct FP4 tensor K dimension in grouped blockscaled GEMM
inactive-30d
#3102
opened Mar 13, 2026 by
Hale423
Loading…
Add dlopen-based dynamic kernel loading for profiler
inactive-30d
#3088
opened Mar 3, 2026 by
Wazrrr
Loading…
fix: Use is_family_of() for SM90 arch guard in warpgroup MmaOp
#3084
opened Feb 28, 2026 by
blake-snc
Loading…
minor: remove deprecated dynamic_expr in the example
inactive-30d
#3073
opened Feb 26, 2026 by
JINO-ROHIT
Loading…
[CuTeDSL] Fix Doc of _binary_op to match current implementation.
inactive-30d
inactive-90d
#3069
opened Feb 25, 2026 by
Peter9606
Contributor
Loading…
[CuTeDSL] Fix: remove redundant Float8E4M3.
inactive-30d
inactive-90d
#3067
opened Feb 25, 2026 by
Peter9606
Contributor
Loading…
[CuTeDSL] DOC:Fix
typing.py URL in the CuTe DSL docs
inactive-30d
#3066
opened Feb 25, 2026 by
vishnoianil
Loading…
[CuTeDSL] Support type checking w/ Constexpr and layout/tensor __repr__
inactive-30d
inactive-90d
#3063
opened Feb 24, 2026 by
Alkaid-Benetnash
Loading…
[CuTeDSL] Add BF16 grouped GEMM example for Hopper SM90
inactive-30d
inactive-90d
#3060
opened Feb 23, 2026 by
vruga
Contributor
Loading…
Use unrounded inputs for the profiler by default
#3053
opened Feb 22, 2026 by
saagarjha
Contributor
Loading…
docs: Fix IDE setup guide for VSCode and clangd
inactive-30d
inactive-90d
#3052
opened Feb 22, 2026 by
bledden
Contributor
Loading…
2 tasks
docs: Fix invalid composition example in cute.composition docstring
inactive-30d
inactive-90d
#3050
opened Feb 21, 2026 by
bledden
Contributor
Loading…
fix: Correct stride calculation in AffineRank2RowMajor::packed()
inactive-30d
inactive-90d
#3048
opened Feb 21, 2026 by
bledden
Contributor
Loading…
cutlass: enable SM121-gated MXFP4 MoE kernel path
#3038
opened Feb 16, 2026 by
christopherowen
Loading…
DOC: fix typo in media/docs/cpp/cutlass_3x_design.md
inactive-30d
inactive-90d
#3035
opened Feb 15, 2026 by
kfpanda123
Loading…
[CuTeDSL] Flash Attention v2 for SM120 (Blackwell GeForce)
#3030
opened Feb 13, 2026 by
blake-snc
Loading…
minor: wrong cordinate in layout algebra docs section
inactive-30d
inactive-90d
#3014
opened Feb 10, 2026 by
JINO-ROHIT
Loading…
Declare CUDA standard 20 as requirement for example 63 (fixes #3011)
#3013
opened Feb 10, 2026 by
reuterbal
Loading…
use compiler macro to imporve the compatibility
inactive-30d
#3008
opened Feb 6, 2026 by
reed-lau
Contributor
Loading…
ProTip!
Find all pull requests that aren't related to any open issues with -linked:issue.