Skip to content

Pull requests: triton-lang/triton

New pull request New
170 Open 6,560 Closed
170 Open 6,560 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

move swizzle func to triton side
#8944 opened Dec 9, 2025 by qnie-oai • Draft
7 tasks
1
Upgrade to PTX 13.1
#8941 opened Dec 8, 2025 by adstraw Loading…
5 tasks done
3
[CONSAN] Adding support for aliasing
#8939 opened Dec 8, 2025 by pawelszczerbuk Loading…
3
[AMD] enable mxfp8 and mxfp4 in test_scaled_dot@test_core.py on GFX1250
#8938 opened Dec 8, 2025 by zwu-2025 Loading…
10
[BENCH] Fix distributed tests
#8937 opened Dec 8, 2025 by Jokeren Loading…
1
[AMD] Add check for cooperative groups support in driver
#8935 opened Dec 8, 2025 by nithinsubbiah Loading…
1
[CMAKE] Canonicalize LLVM_BUILD_SHARED_LIBS before using it in lit.site.cfg.py.in
#8933 opened Dec 8, 2025 by ShujianQian Loading…
4 of 6 tasks
[PROTON] Implement the get_data api to export profile directly in Python
#8928 opened Dec 8, 2025 by Jokeren Loading…
[Tests] Fix assert bug for fp8e5 dot on sm120.
#8927 opened Dec 7, 2025 by Rayfxl Loading…
5 of 7 tasks
2
Add support for CUDA 13.0+ in ptx_get_version
#8925 opened Dec 6, 2025 by ChrisFab16 Loading…
7 tasks
1
[BACKEND] Don't crash on an assert when using M=64 & 2CTA mode
#8922 opened Dec 6, 2025 by lezcano Loading…
3
[Backend] Bump to llvm/llvm-project@a992f294
#8919 opened Dec 6, 2025 by antiagainst • Draft
Add support for assignment ("walrus") expressions
#8913 opened Dec 5, 2025 by saagarjha Loading…
5 of 7 tasks
[AMD] using a deterministic order if possible
#8911 opened Dec 5, 2025 by Dewei-Wang-sh • Draft
3
[do not review] optimize mxfp8 ragged
#8904 opened Dec 4, 2025 by jongsoo-openai • Draft
7 tasks
1
[BACKEND] Disable maybeDeduplicate for AMDWmma
#8901 opened Dec 4, 2025 by kelesvol Loading…
5 of 7 tasks
4
[AMD] refactor proton to use rocprofiler-sdk and deprecate roctracer
#8894 opened Dec 3, 2025 by ZelboK • Draft
[WS] Correctly assign stage / cluster annotation to aref ops for a block-arg producer
#8883 opened Dec 3, 2025 by masahi Loading…
11
TritonGPUToLLVM: Set target specific function attibutes in TargetInfo
#8856 opened Dec 1, 2025 by kelesvol Loading…
5 of 7 tasks
1
Use pyrefly for type checking
#8855 opened Dec 1, 2025 by rchen152 Loading…
5 of 7 tasks
5
[Tutorials] Fix persistent matmul tutorial grouped indexing
#8852 opened Nov 27, 2025 by Aladoro Loading…
5 of 7 tasks
[WIP][BACKEND] Generalize the MemBar to consider cross-CTA ops
#8834 opened Nov 25, 2025 by lezcano • Draft
16
Avoid using block_m=64 when having mxfp8 downcast in epilogue
#8830 opened Nov 25, 2025 by qnie-oai • Draft
7 tasks
1
refine lds layout order for transposed input
#8827 opened Nov 24, 2025 by scxiao • Draft
5 of 7 tasks
3
add bailout for estimation and benchmarking in autotuning
#8816 opened Nov 24, 2025 by krillillin Loading…
5 of 7 tasks
7
ProTip! Find all pull requests that aren't related to any open issues with -linked:issue.