Skip to content

Pull requests: triton-lang/triton

New pull request New
149 Open 6,223 Closed
149 Open 6,223 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] Simplify lowering of ds_read_tr
#8525 opened Oct 24, 2025 by nzaghen • Draft
1
Triton Dialect Plugins, first attempt
#8523 opened Oct 23, 2025 by plotfi • Draft
[DRAFT][LL] LL Python Interface
#8521 opened Oct 23, 2025 by Jokeren Loading…
10
Use out_dtype instead of element_size for microscaling condition
#8519 opened Oct 23, 2025 by wdziurdz Loading…
4 of 7 tasks
1
Wrap datatypes into contexprs
#8513 opened Oct 23, 2025 by Myrthan Loading…
5 of 7 tasks
1
Compile-time logging improvement
#8506 opened Oct 21, 2025 by agorenstein-nvidia Loading…
5 tasks done
3
[AMD][Draft] Optimize reduce waves layout
#8500 opened Oct 21, 2025 by Liang-jianhao97 • Draft
5 of 7 tasks
6
[frontend] Disable cache when interpreter is enabled
#8499 opened Oct 21, 2025 by rpelke Loading…
4 of 7 tasks
[WIP] [WS] Optimize codegen for loop carried dependencies
#8497 opened Oct 21, 2025 by GrumbleMonkey Loading…
3 of 7 tasks
1
[AMD][GLUON] Expose get wmma/mfma scale layout
#8496 opened Oct 20, 2025 by borontion Loading…
4
[RELAND][LAYOUTS] Generate distributed layouts for tcgen05.ld/st generically (#8421)
#8495 opened Oct 20, 2025 by lezcano Loading…
2
Fix get_int_dtype error in triton 3.5 to fix TransformerEngine
#8486 opened Oct 20, 2025 by fzyzcjy Loading…
7 tasks
[DO NOT MERGE] 3.5.0 + masahi's PR8045
#8485 opened Oct 20, 2025 by fzyzcjy Loading…
[TRITON_KERNELS] Support sm120 / 121 via sm80 fallback
#8484 opened Oct 19, 2025 by masahi Loading…
11
Phil/matmul cleanup
#8483 opened Oct 19, 2025 by ptillet • Draft
2
[RFC] Add local scatter/gather for Gluon
#8480 opened Oct 19, 2025 by nhukc Loading…
5 of 7 tasks
21
Rename NVGPU to NVG
#8466 opened Oct 17, 2025 by wsmoses Loading…
1
[AMD] Optimize address increments for buffer loads in loops
#8464 opened Oct 16, 2025 by alefimov-amd • Draft
[TritonNvidiaGPU] Add int8 MMAv5 support to TCGen5MMAOp
#8463 opened Oct 16, 2025 by christopherbate Loading…
2 tasks
5
[triton_kernels][swiglu] Add standard implementation of swiglu
#8460 opened Oct 16, 2025 by matkle Loading…
[triton_kernels][opt_flags] Add function to reset opt_flags
#8453 opened Oct 16, 2025 by matkle Loading…
[AMD][Draft] Implement implicit layout conversion for DotOp to enable direct GMEM to reg loads
#8450 opened Oct 16, 2025 by the-strawhat Loading…
1
[AMD][Draft] Eliminate redundant matmul by adjusting HeadDot wavefront partitioning
#8449 opened Oct 16, 2025 by the-strawhat Loading…
1
Fix autotune thread safety (crash) under GIL=0
#8437 opened Oct 13, 2025 by Qubitium Loading…
5 tasks done
15
[Backend] Bump tp llvm/llvm-project@4a3e0001e367
#8436 opened Oct 13, 2025 by ravil-mobile • Draft
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.