Skip to content

Pull requests: triton-lang/triton

New pull request New
52 Open 3,523 Closed
52 Open 3,523 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
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Pull requests list

Updated README.md to show the steps for overriding kernel's IR
#5239 opened Nov 22, 2024 by arakhmati-openai Loading…
[LAYOUTS] Use LLs for Hopper whenever we wouldn't use ldmatrix
#5235 opened Nov 22, 2024 by lezcano Loading…
[BUILD] Add a stable symlink to llvm in the triton cache
#5234 opened Nov 22, 2024 by peterbell10 Loading…
Atomic rmw mask
#5231 opened Nov 22, 2024 by scxiao • Draft
4 of 7 tasks
[AMD] Upgrade AMD CI docker image
#5230 opened Nov 22, 2024 by AlexAUT • Draft
5 of 7 tasks
1
[AMD] Improve codebase style consistency in third_party/amd
#5229 opened Nov 22, 2024 by knwng • Draft
4 of 7 tasks
1
[AMD] remove driver C compilation steps
#5228 opened Nov 22, 2024 by makslevental • Draft
3
[AMD] Pipeline small vector width but not thru shared memory
#5227 opened Nov 22, 2024 by sjw36 • Draft
1
[AMD] inThreadTranspose: Transpose between global load and local store for non-TN layouts: part 2 of 4
#5223 opened Nov 21, 2024 by jtang10 • Draft
2 of 4 tasks
[NVIDIA][Backend] Add CoalesceAsyncCopy Pass for in-DotOpEnc Upcasting
#5222 opened Nov 21, 2024 by ggengnv Loading…
5
[DRAFT][FRONTEND] added support for tuples
#5220 opened Nov 21, 2024 by ptillet • Draft
8
[CI] Add ASAN libs to CI script
#5209 opened Nov 21, 2024 by CRobeck • Draft
Add support for 3-5D TMA to allow loading non-matmul operands
#5207 opened Nov 21, 2024 by masahi Loading…
5 of 7 tasks
12
[AMD] release/3.2.x AMD perf cherry picks
#5191 opened Nov 19, 2024 by jataylo • Draft
Atomic Load and Store operations for Triton (tl.atomic_store/tl.atomic_load)
#5187 opened Nov 19, 2024 by plotfi • Draft
5 tasks done
3
Windows related changes in CMakeLists.txt
#5186 opened Nov 18, 2024 by anmyachev Loading…
9
Support computation pipelining after SWP refactoring
#5185 opened Nov 18, 2024 by manman-ren • Draft
1
[PIPELINER] Cleanup of LoopScheduling.cpp, introduction of AssignLatencies
#5176 opened Nov 15, 2024 by pawelszczerbuk Loading…
12
[AMD] Add instruction schedule loop boundary guard hints
#5163 opened Nov 15, 2024 by ravil-mobile • Draft
5 of 7 tasks
36
[Tutorial] Remove incorrect caching from softmax tutorial
#5162 opened Nov 15, 2024 by Mogball Loading…
2
[BACKEND][DRAFT] Use linear layout for loading mmav2 dot operand tensors from shared memory
#5154 opened Nov 14, 2024 by Jokeren • Draft
Create an aggregate check-triton-unit target
#5150 opened Nov 14, 2024 by Mogball Loading…
3
[AMD] inThreadTranspose: Transpose between global load and local store for non-TN layouts: part 1 of 4
#5148 opened Nov 14, 2024 by jtang10 • Draft
6 of 11 tasks
43
feat: Dev Container for consistent dev setup
#5143 opened Nov 14, 2024 by maryamtahhan Loading…
5 of 7 tasks
4
[AMD] Fixed instruction reorder
#5130 opened Nov 12, 2024 by ravil-mobile • Draft
4 of 7 tasks
1
ProTip! Follow long discussions with comments:>50.