Skip to content

Pull requests: triton-lang/triton

New pull request New
167 Open 7,017 Closed
167 Open 7,017 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

[BACKEND] Refactor forward layout propagation
#9463 opened Feb 13, 2026 by ThomasRaoux Loading…
11
2CTA Block Scale MMA with tcgen05.cp
#9460 opened Feb 13, 2026 by adstraw Loading…
5 of 7 tasks
15
[BUILD] Move third party package downloads from setup.py to CMake codex
#9458 opened Feb 13, 2026 by peterbell10 • Draft
[BACKEND] Make cluster barriers be executed by all the threads
#9456 opened Feb 13, 2026 by lezcano Loading…
8
[AMD] Enable floating-point sanitizer (FpSan) support
#9455 opened Feb 13, 2026 by kelesvol Loading…
2
[NFCi][triton-ext] Reorganizing how libtriton's linkage visibility and build setup
#9453 opened Feb 13, 2026 by plotfi • Draft
[TritonGPU] Make MMA instr-shape inference fail-safe and add unit tests
#9452 opened Feb 13, 2026 by jeongseokson Loading…
5 of 7 tasks
2
[WIP][AMD] Added hw FP upcast conversions for gfx1250
#9449 opened Feb 13, 2026 by ravil-mobile • Draft
4
[runtime] Allow explicit unload compiled kernel module
#9444 opened Feb 12, 2026 by scxiao • Draft
5 of 7 tasks
3
[AMD][BACKEND] Fix OOM bug in pipelining with padded layout async copy on GFX950
#9442 opened Feb 12, 2026 by pabloantoniom Loading…
5 of 7 tasks
3
Fix import torch bomb in HIPBackend
#9441 opened Feb 12, 2026 by Arech8 Loading…
4 of 7 tasks
2
Clarify which Python requirements to install
#9436 opened Feb 11, 2026 by abrown Loading…
2
Fix autotuner cache serialization for non-string tuning keys
#9429 opened Feb 11, 2026 by fsx950223 Loading…
7 tasks
[TensorDescriptor] Support kernel tuple arguments containing descriptors
#9422 opened Feb 10, 2026 by peterbell10 Loading…
2
[AMD][Membar] Add MemAsyncLocalWriteOpTrait for cleaner async ops filtering.
#9418 opened Feb 10, 2026 by jungpark-mlir Loading…
24
[AMD][WIP] LDS Prefetch Pass to support slicing M, N
#9411 opened Feb 9, 2026 by guacamoleo • Draft
13
[Nvidia] Enable TMA im2col mode - Tutorial
#9406 opened Feb 9, 2026 by bingyizh233 Loading…
5 tasks done
52
[UT] Use numpy.concatenate instead of numpy.concat
#9399 opened Feb 7, 2026 by lijinpei-amd • Draft
7 tasks
1
[Kernels] Enable persistent matmul for fp32 inputs
#9393 opened Feb 6, 2026 by ThomasRaoux Loading…
2
Make compute_block_n produce N divisible by 128 for Blackwell scales
#9389 opened Feb 6, 2026 by roman-openai Loading…
[AMD][Test] Reenable test_hooks() for HIP CDNA2
#9388 opened Feb 5, 2026 by yiqian1 • Draft
Add scatter with reduction support
#9379 opened Feb 5, 2026 by denix56 Loading…
5 of 7 tasks
3
[WIP] Change default precision of tl.dot to ieee
#9377 opened Feb 4, 2026 by ThomasRaoux • Draft
Column major output support in persistent matmul
#9339 opened Jan 30, 2026 by farzad-openai Loading…
5 of 7 tasks
[WIP] Triton Tensor sharding
#9323 opened Jan 29, 2026 by tudor-openai Loading…
ProTip! Type g i on any issue or pull request to go back to the issue listing page.