-
Notifications
You must be signed in to change notification settings - Fork 2.1k
Pull requests: NVIDIA/cutlass
Author
Label
Projects
Milestones
Reviews
Assignee
Sort
Pull requests list
examples/64: relax exact CC 8.9 gate to inclusive check
#3586
opened Sep 5, 2026 by
SAR2652
Loading…
Size SM100/SM103 array GEMM tensormap workspace from the device SM count
#3584
opened Sep 4, 2026 by
elbourne12345
Loading…
Fix handling of JAX tensor types without TVM FFI and leading dim deduction for all-1-size tensors
#3583
opened Sep 4, 2026 by
dextero
Loading…
Fix Constexpr method receivers in dynamic control-flow regions
#3580
opened Sep 3, 2026 by
nodeeeeee
Loading…
Fix skipped workspace initialization for parallel split-K in GemmUniversalBase
#3578
opened Sep 1, 2026 by
AyaanFaisal21
Loading…
Copy the imaginary halves of the inputs in MmaPlanarComplex
#3575
opened Sep 1, 2026 by
darkdi
Loading…
Move dense_gemm_cute_pipeline.py under dense_gemm/ to make it consistent with other examples.
#3574
opened Sep 1, 2026 by
Junkai-Wu
Collaborator
Loading…
Fix cute.composition rejecting dynamic-shaped RHS modes with a ScaledBasis stride
#3572
opened Aug 30, 2026 by
saiyambharara
Loading…
Fix ArraySubbyte logical back and iterator bounds
#3569
opened Aug 29, 2026 by
migarci2
Contributor
Loading…
Fix SFB shared memory layout major selection
#3566
opened Aug 28, 2026 by
migarci2
Contributor
Loading…
[CuTeDSL] Fix blockwise GEMM opt-level version gate
#3563
opened Aug 28, 2026 by
myu-guo
Contributor
Loading…
[Examples] Fix wgrad workspace dump tensor and swapped grid/block in FMHA reference
#3561
opened Aug 28, 2026 by
SuperGoodGame
Loading…
[conv] Fix degenerate spatial extent calculation, grouped channel sizing, and add device wrapper validation tests
#3559
opened Aug 27, 2026 by
Sadik00789
Loading…
Correct host reference MRE padded diagonal fill and Gaussian seed
#3554
opened Aug 26, 2026 by
Hashim1999164
Loading…
Previous Next
ProTip!
What’s not been updated in a month: updated:<2026-08-05.