Skip to content

Pull requests: triton-lang/triton

New pull request New
95 Open 5,159 Closed
95 Open 5,159 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] Assert that num threads is always power of 2 (NFC)
#7251 opened Jun 20, 2025 by Mogball Loading…
[AMD][BACKEND] Do not pipeline via AsyncCopyGlobalToLocal if the load width is less than 32bit
#7250 opened Jun 20, 2025 by AlexAUT Loading…
2
[Layouts] Infer slice encoding for SplitOp result
#7247 opened Jun 20, 2025 by peterbell10 Loading…
6
[AMD] Fix pointer canonicalizer when propagating discardable attrs
#7242 opened Jun 19, 2025 by nzaghen • Draft
5 of 7 tasks
5
[IR] tune the rematerialization heuristic to avoid harmful rematerialization
#7240 opened Jun 19, 2025 by ywq880611 Loading…
5 of 7 tasks
1
3
Allow customization of the subscript operator for triton values
#7239 opened Jun 19, 2025 by Anstow Loading…
5 of 7 tasks
1
[WIP][Gluon][Tutorial] Optimize attention kernel
#7238 opened Jun 19, 2025 by Mogball • Draft
1
[wip] Logging debug info before async ops
#7231 opened Jun 18, 2025 by dhruvmk Loading…
5 of 7 tasks
[AMD] expose core pipeliner utilities and integrate in AMD pipeliner
#7222 opened Jun 18, 2025 by makslevental Loading…
4
[Backend] Add a shared layout for padding
#7212 opened Jun 18, 2025 by antiagainst Loading…
20
Improve detection of loop carries in triton frontend
#7200 opened Jun 17, 2025 by Anstow Loading…
5 of 7 tasks
7
[Bench][AMD]Fix Maximal BW Calculation and Add Gfx950 Specs
#7175 opened Jun 12, 2025 by knwng • Draft
Insert random delays to debug races/deadlocks
#7174 opened Jun 12, 2025 by dhruvmk Loading…
5 of 7 tasks
[ConSan] Concurrency Sanitizer - initial scaffolding and introduction of TritonInstrument dialect
#7157 opened Jun 11, 2025 by pawelszczerbuk Loading…
11
[BACKEND] Clean up hard code for NV and AMD GPU in the common TritonGPU dialect to support third party GPU extension.
#7147 opened Jun 11, 2025 by chengjunlu Loading…
[Hopper][WS] Update pipeline to get GEMM/FA working
#7136 opened Jun 10, 2025 by manman-ren Loading…
38
[AMD] Rewrite extract_slice op implementation
#7128 opened Jun 10, 2025 by plognjen Loading…
22
[do_bench] synchronize before first function call
#7124 opened Jun 10, 2025 by nmacchioni Loading…
5 of 7 tasks
1
[AMD][InThreadTranspose] Support chains without global load
#7117 opened Jun 9, 2025 by joviliast Loading…
7
[BACKEND] Extend interleave tmem to hoist tmem_store
#7111 opened Jun 9, 2025 by ThomasRaoux Loading…
1
Fix pipelining of mixed WGMMA and non-WGMMA usage
#7110 opened Jun 9, 2025 by jhapradip Loading…
5 of 7 tasks
1
2
Documentation for running Triton Community Meetups.
#7103 opened Jun 6, 2025 by byoshimi-gmail Loading…
2 tasks
2
Build with -Wunused-variable
#7049 opened Jun 4, 2025 by ayshuha Loading…
5 of 7 tasks
[Tutorial] Fix 06-fused-attention.py of FP8 provider
#7043 opened Jun 4, 2025 by whitneywhtsang Loading…
11
[WIP] [AMD] [NVIDIA] Support fp8 types in ty_to_cpp
#7039 opened Jun 3, 2025 by njriasan • Draft
ProTip! Mix and match filters to narrow down what you’re looking for.