Skip to content

Pull requests: triton-lang/triton

New pull request New
102 Open 5,587 Closed
102 Open 5,587 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

[AMD] Enable FP4 pack along M/N tests for CDNA4
#7736 opened Aug 1, 2025 by nzaghen • Draft
[Tests] Use tmp_path pytest fixture instead of tempfile.NamedTemporaryFile
#7735 opened Aug 1, 2025 by anmyachev Loading…
3
[NVWS] Support tmem_alloc(desc_load()) pattern in aref insertion
#7734 opened Aug 1, 2025 by masahi Loading…
1
[FRONTEND] Add option to disable licm on for and while loops
#7733 opened Aug 1, 2025 by ThomasRaoux Loading…
1
[Hopper] Handle WGMMA wait with 0 deps
#7732 opened Aug 1, 2025 by Mogball Loading…
1
[Gluon] Expose DotOperandLayout
#7730 opened Aug 1, 2025 by Mogball Loading…
1
[PROTON] Capture global timestamps for consistent cross-CTA timeline
#7729 opened Jul 31, 2025 by ShawnZhong Loading…
5 tasks done
[OAI] Exclude function from being wrapped in tl.constexpr()
#7724 opened Jul 31, 2025 by hgreving2304 Loading…
4 of 7 tasks
1
[WIP] [AMD] Investigate custom epilogue peeling
#7721 opened Jul 31, 2025 by PMylon • Draft
[AMD] knob for within_2gb check for specialization
#7720 opened Jul 31, 2025 by makslevental Loading…
1
[ConSan] Support for WGMMA. Checks on non-async shmem and tmem accesses
#7712 opened Jul 30, 2025 by pawelszczerbuk Loading…
Add python 3.14 wheel build
#7695 opened Jul 29, 2025 by atalman Loading…
3
[Kernels] Add a few redundant tensor attribute to be compatible with torch.Tensor
#7688 opened Jul 28, 2025 by zyongye Loading…
5 of 7 tasks
9
[Hopper][WS] Add named barriers and a basic algorithm to enforce ping pong of the critical resource
#7678 opened Jul 28, 2025 by manman-ren • Draft
7
[mxfp] support quant/dequant from/to fp32
#7672 opened Jul 28, 2025 by jongsoo-openai Loading…
5 of 7 tasks
2
[mxfp] fix bug with fused_scatter
#7671 opened Jul 28, 2025 by jongsoo-openai Loading…
5 of 7 tasks
4
[WIP][AMD]Separate Schedule Building with Loop Rewriting in StreamPipeline
#7660 opened Jul 25, 2025 by knwng • Draft
[WIP][Gluon][Tutorials] Tutorials
#7657 opened Jul 25, 2025 by Mogball • Draft
[AMD][GLUON] expose amd_mfma layout
#7653 opened Jul 25, 2025 by zwu-2025 Loading…
4 tasks done
56
[AMD] Padded shared layout in In Thread Transpose
#7647 opened Jul 24, 2025 by alefimov-amd • Draft
2
[AMD] Support scaled dot gfx12
#7644 opened Jul 24, 2025 by joviliast Loading…
9
Combine all prerequisite checks of tl.dot into dot_precheck
#7639 opened Jul 24, 2025 by dshi7 Loading…
2
Triton debuginfo
#7633 opened Jul 23, 2025 by Youngzt998 • Draft
7 tasks
9
[AMD] Enable global_load_tr_b128 on gfx12
#7616 opened Jul 23, 2025 by ptrojahn • Draft
33
[DNR][WIP][NVWS] introduce nvws.semaphore
#7612 opened Jul 23, 2025 by 3gx Loading…
7 tasks
4
ProTip! Mix and match filters to narrow down what you’re looking for.