Skip to content

Pull requests: NVIDIA/cutlass

New pull request New
124 Open 840 Closed
124 Open 840 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Reviews
Filter by reviews
No reviews Review required Approved review Changes requested
Assignee
Filter by who’s assigned
Assigned to nobody Loading
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

[Fix] distributed gemm all reduce and reduce scatter examples
#3143 opened Apr 1, 2026 by Nicyzk Loading…
correct BLayout stride in SM80 m16n8k32 int4 MMA traits
#3140 opened Apr 1, 2026 by zfmmmm Loading…
Fix Hopper FMHA performance regression on CUDA < 13.1
#3137 opened Mar 31, 2026 by arvin-chou Loading…
5 of 6 tasks
feat(CuTeDSL): print benchmark time from Blackwell dense_gemm CLI
#3136 opened Mar 30, 2026 by aidando73 Loading…
1
[CuTeDSL] Add a render function hook to allow render layout natively
#3135 opened Mar 30, 2026 by kainzhong Loading…
Fix incorrect warp arrangement in PitchLinearWarpStripedThreadMap
#3131 opened Mar 25, 2026 by HaoYuan-Gao Loading…
Update blackwell tutorial to be compatible with 4.5-dev version
#3130 opened Mar 25, 2026 by LongshengDu • Draft
Fix elementwise_apply.py
#3129 opened Mar 25, 2026 by HydraQYH Loading…
[CuTeDSL] Add SM103 grouped block-scaled GEMM kernel and tests
#3124 opened Mar 23, 2026 by Johnsonms Loading…
Enable strict C++ compiler warnings with -Werror
#3123 opened Mar 22, 2026 by maxwbuckley Loading…
3 of 4 tasks
fix: Handle zero-stride TMA basis in fill_tma_gmem_shape_stride
#3121 opened Mar 20, 2026 by RobTand Loading…
2 tasks
14
[bugfix] use acquire to prevent reordering.
#3118 opened Mar 20, 2026 by shubaoyu2 Loading…
1
Fix typo in elementwise_add.py
#3116 opened Mar 20, 2026 by HydraQYH Loading…
Add FlashMoE Publication
#3115 opened Mar 20, 2026 by osayamenja Loading…
1
[FMHA] Add SM110 support for Blackwell FMHA example (77_blackwell_fmha)
#3112 opened Mar 18, 2026 by LiangSu8899 Loading…
fix(CuTeDSL): correct FP4 tensor K dimension in grouped blockscaled GEMM
#3102 opened Mar 13, 2026 by Hale423 Loading…
1
[docs] Fix same typo
#3098 opened Mar 9, 2026 by lhtin Loading…
[CuTe] adding DSL INT8 MMA support on SM80+, with CuTe C++ example
#3097 opened Mar 9, 2026 by ayghri Loading…
WIP: OSS CI Testing for v4.4
#3093 opened Mar 7, 2026 by zekunf-nv Loading…
5
Add dlopen-based dynamic kernel loading for profiler
#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…
1
fix: Use is_family_of() for SM12x arch guard in MmaSM120BlockScaledOp
#3082 opened Feb 27, 2026 by blake-snc Loading…
2
[Cute-DSL] Fix runtime shared library loading for TVM FFI Module Loading
#3075 opened Feb 26, 2026 by Alkaid-Benetnash Loading…
3
minor: remove deprecated dynamic_expr in the example inactive-30d
#3073 opened Feb 26, 2026 by JINO-ROHIT Loading…
3
[CuTeDSL] Fix Doc of _binary_op to match current implementation. inactive-30d
#3069 opened Feb 25, 2026 by Peter9606 Loading…
1
ProTip! Filter pull requests by the default branch with base:main.