Skip to content

Pull requests: NVIDIA/cutlass

New pull request New
168 Open 904 Closed
168 Open 904 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

insignificant typo
#3320 opened Jun 15, 2026 by igodlab Loading…
[CuteDSL] Fix source location info for cute.arch.elect_one
#3317 opened Jun 14, 2026 by pchen7e2 Loading…
[Tutorial] Fix race condition in 2SM TMEM alloc for Cute Blackwell Tutorial 04/05
#3316 opened Jun 14, 2026 by pchen7e2 Loading…
[docs/examples] Blackwell tutorial 04 (2SM MMA): fix stale B-operand print annotations (the 2x1SM atom splits B N/2-per-CTA) and document the expect-tx pitfalls that deadlock
#3314 opened Jun 11, 2026 by cfregly Loading…
[docs/examples] Blackwell cute tutorials: narrow TMEM_LOAD atoms (32dp32b1x) carry a large per-load lowering cost — prefer wider atoms (32dp32b32x) in t2r epilogues
#3313 opened Jun 11, 2026 by cfregly Loading…
[CuTeDSL] Fix _ScalarData internal methods triggering its own struct.scalar deprecation
#3311 opened Jun 10, 2026 by Johnsonms Contributor Loading…
quick fix for fmha_bwd regressions
#3309 opened Jun 9, 2026 by Jie-Fang Loading…
1
Fix CUTLASS Blackwell FMHA register spills on DRIVE Thor (sm_110a)
#3308 opened Jun 8, 2026 by pzhao-eng Loading…
Fixed integer overflow in make_cute_packed_stride batch stride computation
#3307 opened Jun 7, 2026 by a123pal Loading…
1
Fix QNX fill_workspace status
#3306 opened Jun 6, 2026 by fallintoplace Loading…
Fix Python ctypes signatures
#3305 opened Jun 6, 2026 by fallintoplace Loading…
Enable smem_merge_branch_allocs option on branched mega-kernel examples
#3304 opened Jun 5, 2026 by LongshengDu Contributor Loading…
adding DSL INT8 MMA support on SM80+, with CuTe C++ example
#3302 opened Jun 5, 2026 by ayghri Loading…
Fix CUDA 12.8 __nv_atomic_load_n call signature in SubbyteReference
#3301 opened Jun 5, 2026 by wanghemeng Loading…
Fix print_tensor self-contained include
#3300 opened Jun 5, 2026 by Rohithmatham12 Loading…
1
add tileN = 8,16 for SM120 blockscale GEMM.
#3292 opened Jun 2, 2026 by b8zhong Loading…
5
[CuTeDSL] Add docs of how to call cute.jit functions in C++ via TVM-FFI
#3289 opened Jun 1, 2026 by kainzhong Loading…
8
feat: Add BF16 float-accumulator TensorOp epilogue specialization
#3287 opened Jun 1, 2026 by lyuxy-infra Loading…
fix: missing PDL wait on main_sf_load in sm103 blockscaled GEMM
#3279 opened May 27, 2026 by tianyuxbear Loading…
Fix the ScatterD issue in predicated_tile_iterator
#3278 opened May 27, 2026 by pengpeng-yu Loading…
1
[CuTeDSL] Fix the incorrect import of from_dlpack from docs
#3276 opened May 26, 2026 by kainzhong Loading…
1
[CuTeDSL] Add SM120 MXF4/NVFP4 native-TMA path
#3273 opened May 25, 2026 by alecco Loading…
[CuTeDSL] Lower scalar Float16/BFloat16 load through Uint16+bitcast
#3267 opened May 24, 2026 by cheshire Contributor Loading…
1
1
fix: handle ComposedLayout slicing with dynamic strides (fixes #3255)
#3261 opened May 22, 2026 by zhils Loading…
fix(CuTeDSL): restore trailing Int<1> dimension in SM90 MMA atom TV L…
#3258 opened May 21, 2026 by zhils Loading…
1
1
ProTip! Add no:assignee to see everything that’s not assigned.