Skip to content

Pull requests: NVIDIA/cutlass

New pull request New
195 Open 942 Closed
195 Open 942 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

docs: fix broken CuTe DSL educational notebook links
#3431 opened Aug 3, 2026 by felipeofdev-ai Loading…
1 of 2 tasks
1
1
Add CuTeDSL math tests for sqrt operation
#3430 opened Aug 3, 2026 by Pritiks23 Loading…
Fix ScaledBasis equality for mismatched bases, add SM120 sparse metadata K assert
#3427 opened Jul 31, 2026 by davidkny22 Contributor Loading…
[CuTe DSL] Fix REPL crash: clear diagnostic and keep the interpreter alive (issue #3413)
#3424 opened Jul 30, 2026 by layahaasini Loading…
1
5
Fix GC-cycle leak: drop frame self-references in CuTe DSL decorators
#3423 opened Jul 30, 2026 by thakkarV Contributor Loading…
1
Docs: Remove dynamic_expr from examples; deprecated since v4.1
#3422 opened Jul 30, 2026 by janekb04 Loading…
[CuTeDSL] Add prepared-launch API for low-overhead kernel replay
#3419 opened Jul 29, 2026 by zkyue Contributor Loading…
1
[CuTeDSL] Fix prep_editable_install.py for split nvidia-cutlass-dsl wheels
#3417 opened Jul 29, 2026 by zkyue Contributor Loading…
1
1
Distributed SM100 Syrk AR, SM100 Dynamic Scheduler GEMM AR, Fix Old API
#3412 opened Jul 27, 2026 by XiaoSongXS Member Loading…
Fix pre-Blackwell validation in the Ada FP8 GEMM example
#3411 opened Jul 27, 2026 by Lec16sf Loading…
Require CUDA 12.9 for SM121 default architectures
#3410 opened Jul 26, 2026 by davidkny22 Contributor Loading…
[CuTeDSL] Make autotuning more user friendly & new docs
#3408 opened Jul 24, 2026 by kainzhong Contributor Loading…
[CuTeDSL] Let cute.compile opt into the compile cache
#3402 opened Jul 22, 2026 by aryanputta Loading…
[examples] Fix stale thread layout comment in wgmma_sm90.cu
#3401 opened Jul 21, 2026 by SriRangaTarun Contributor Loading…
1
[Hopper CuTeDSL] Fix max reduction in fmha kernel
#3399 opened Jul 20, 2026 by Aladoro Loading…
[CuTe DSL] Raise a clear error when jit source is stale instead of silently misbehaving, issue #3395
#3396 opened Jul 19, 2026 by yunweili3 Loading…
Fix SM89 FP8 blockwise scale indexing under threadblock swizzling
#3394 opened Jul 18, 2026 by Noperi0r Loading…
1
Fix CuTe tuple protocol compatibility across CCCL versions
#3386 opened Jul 14, 2026 by xiufanl Contributor Loading…
2
[CuTeDSL] Allow reassoc fastmath flag on vector reduction ops
#3384 opened Jul 13, 2026 by antoniofrighetto Loading…
7
fix: restrict i8-to-bf16 arch gate to Hopper+ and guard s2t copy to leader CTA
#3380 opened Jul 10, 2026 by Functionhx Loading…
1
docs: remove empty duplicate Numeric Conversion section
#3379 opened Jul 9, 2026 by Functionhx Loading…
1
Add tuning notes for Hopper 16-bit dense GEMM
#3373 opened Jul 7, 2026 by hamuzhan Loading…
Prune SM90 kernel configs whose accumulator does not fit in registers
#3372 opened Jul 7, 2026 by hamuzhan Loading…
5
Enable SM110 for Blackwell FMHA and warpgroup reg reconfig inactive-30d
#3360 opened Jul 1, 2026 by denverlloyd-debug Loading…
1
Update MLA decode example inactive-30d
#3357 opened Jun 30, 2026 by Observer007 Contributor Loading…
1
ProTip! no:milestone will show everything without a milestone.