Skip to content

Pull requests: NVIDIA/cutlass

New pull request New
95 Open 759 Closed
95 Open 759 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 Mode Name and Stride in 0t_mma_atom.md
#2910 opened Dec 27, 2025 by HydraQYH Loading…
Fix CUDA version checking in examples
#2894 opened Dec 21, 2025 by aychun Loading…
docs: note when DSL dumps are populated
#2891 opened Dec 20, 2025 by ColinPeppler Loading…
1
Fix finding cuDNN
#2890 opened Dec 19, 2025 by TLescoatTFX Loading…
1
fix typo
#2884 opened Dec 17, 2025 by kf-zhang Loading…
[cute] Add constexpr specifier to make_tiled_copy
#2875 opened Dec 12, 2025 by tsu-bin Loading…
docs: Add FP16 GEMM documentation to sgemm_sm80.cu - Fixes #1686
#2870 opened Dec 10, 2025 by blueberrycongee Loading…
1
Unit tests for Kernels that perform BF16 x BF16 = MXFP8 and MXFP8 x MXFP8 = BF16
#2857 opened Dec 8, 2025 by Shreya-gaur Loading…
Remove redundant "from" from comment
#2853 opened Dec 8, 2025 by crcrpar Loading…
add SM75_16x8x8_F16F16F16F16_TN
#2851 opened Dec 6, 2025 by jinzhen-lin Loading…
1
use cp.async.bulk for per-row data; quiets synccheck
#2850 opened Dec 5, 2025 by v0i0 Loading…
1
Add spin_lock_atom_cas_acquire_wait function
#2846 opened Dec 5, 2025 by aleozlx Loading…
5
Remove deprecated newshape argument.
#2844 opened Dec 4, 2025 by Artem-B Loading…
Fix TMEM address read/write race in example 77
#2835 opened Dec 3, 2025 by milesvant • Draft
3
Add alignment checks for mx dtypes under the Auto policy
#2827 opened Dec 1, 2025 by Hyaloid Loading…
[DOCS] Update docs to precisely describe env stream scenario
#2824 opened Nov 29, 2025 by tqchen Loading…
[FIX] Update nvidia-cutlass-dsl requirements version from 4.3.0 to 4.3.1
#2823 opened Nov 29, 2025 by jeromeku Loading…
[CuTeDSL] Feature/fp8e4m3 to fp16 conversion
#2822 opened Nov 28, 2025 by arseniivanov Loading…
1
Fix processing of relative imports in AST preprocessing
#2821 opened Nov 28, 2025 by danieldk Loading…
1
Example77 blackwell FMHA decode attention optimization
#2816 opened Nov 25, 2025 by Alkaid-Benetnash Loading…
8
Enable setuptools_scm-based versioning and update build configuration
#2815 opened Nov 25, 2025 by vshawrh Loading…
1
5
Remove x premission of CMakeLists.txt inactive-30d
#2811 opened Nov 25, 2025 by Rtoax Loading…
1
DOC: Fixing fundamental types codeblock inactive-30d
#2803 opened Nov 23, 2025 by SwayamInSync Loading…
4
DOC: Update CUTLASS quickstart, remove FP8 GEMM link inactive-30d
#2799 opened Nov 22, 2025 by SwayamInSync Loading…
1
add cute.union inactive-30d
#2788 opened Nov 21, 2025 by v0i0 Loading…
22
ProTip! Mix and match filters to narrow down what you’re looking for.