Skip to content

Pull requests: triton-lang/triton

New pull request New
58 Open 3,719 Closed
58 Open 3,719 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

[PROTON][DRAFT] Spring 2025 - Core Updates and New Features
#5508 opened Dec 30, 2024 by Jokeren • Draft
[Proton][Dialect] Add Initial Frontend and Target Backend Infrastructure For Proton Dialect
#5506 opened Dec 28, 2024 by CRobeck Loading…
@Jokeren
27
[AMD][Atomic] Introduceruntime LDS reduction algorithm for atomicRmwOp
#5503 opened Dec 26, 2024 by joviliast Loading…
3
[RFC][python] Linting TLC: sort imports through ruff, remove linting/formatting exclusions, generate python/pyproject.toml
#5502 opened Dec 26, 2024 by danzimm • Draft
5 of 7 tasks
5
[AMD] Partially enable test_convert_mma2mma_cases for AMD target
#5495 opened Dec 25, 2024 by binarman • Draft
1
Reduce runtime dependency on torch
#5490 opened Dec 25, 2024 by stephen-huan Loading…
5 of 7 tasks
17
[MXFP] Implement SW emulation of dot_scale as a decomposition
#5475 opened Dec 20, 2024 by lezcano • Draft
[AMD] Refactor lowering math.fdiv with f32 inputs
#5474 opened Dec 20, 2024 by knwng • Draft
5 of 7 tasks
3
Implement conversion from FMA dot operand to linear layout
#5469 opened Dec 19, 2024 by binarman Loading…
1
42
[3.2 cherry pick] Ensure device context before launching kernel (#3731, #5276)
#5465 opened Dec 19, 2024 by bertmaher Loading…
3
[TOOLING] Implement $MLIR_DUMP_PATH to redirect $MLIR_ENABLE_DUMP
#5457 opened Dec 18, 2024 by danzimm Loading…
5 of 7 tasks
4
[release-only] Add triton 3.13t builds
#5455 opened Dec 18, 2024 by atalman Loading…
[AMD] Flush denorms to zero in math.rsqrt
#5438 opened Dec 16, 2024 by knwng • Draft
5 of 7 tasks
1
[WIP] Optimize Autotuner with Parallel Compilation
#5436 opened Dec 16, 2024 by simonidaa Loading…
5 of 7 tasks
10
[AMD] Disable pipelining for loops containing barrier.
#5429 opened Dec 13, 2024 by sjw36 Loading…
8
[AMD] Handling denorms in lowering math.sqrt and math.sqrt_rn
#5422 opened Dec 13, 2024 by knwng • Draft
5 of 7 tasks
[Backend] Implement layout conversion within warps with shuffle idx
#5419 opened Dec 13, 2024 by Mogball Loading…
73
[TOOLS] Move backend template src files to third_party/tools folder
#5411 opened Dec 12, 2024 by ESI-SYD Loading…
5 of 7 tasks
3
[AMD] Support small k dim sizes in MFMA dot operation
#5406 opened Dec 11, 2024 by binarman • Draft
6
[LAYOUTS] Add support for a generic transpose via LLs
#5403 opened Dec 11, 2024 by lezcano Loading…
3
Fix UB in f2reduce for cols == 0
#5401 opened Dec 11, 2024 by chsigg Loading…
5
[LAYOUTS] Add ConvertLayoutOp::fold and remove stale heuristic
#5399 opened Dec 11, 2024 by lezcano • Draft
[AMD] Extended local-prefetch to global_load ops
#5380 opened Dec 9, 2024 by ravil-mobile • Draft
5 of 7 tasks
1
[WIP][SWP] Print recurring dependencies when reporting scheduling conflicts
#5375 opened Dec 9, 2024 by sfzhu93 • Draft
4 of 7 tasks
17
[AMD-Pipeline] Add multi-stage global/local prefetch
#5353 opened Dec 5, 2024 by sjw36 • Draft
ProTip! no:milestone will show everything without a milestone.