Skip to content

Pull requests: pytorch/helion

New pull request New
226 Open 2,892 Closed
226 Open 2,892 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

[CuTe] Generalize FA4 online softmax code generation CLA Signed This label is managed by the Meta Open Source bot.
#3423 opened Aug 19, 2026 by choijon5 Contributor Loading…
[CuTe] Generalize flash target registration and validate lowering contracts CLA Signed This label is managed by the Meta Open Source bot.
#3420 opened Aug 19, 2026 by choijon5 Contributor Loading…
[CuTe] Add SM103 causal resident softmax CLA Signed This label is managed by the Meta Open Source bot.
#3419 opened Aug 19, 2026 by choijon5 Contributor Loading…
[CuTe] Add SM103 dense resident softmax CLA Signed This label is managed by the Meta Open Source bot.
#3418 opened Aug 19, 2026 by choijon5 Contributor Loading…
[CuTe] Add SM103 flash primitives and stat-release topology CLA Signed This label is managed by the Meta Open Source bot.
#3417 opened Aug 19, 2026 by choijon5 Contributor Loading…
[CuTe] Model flash target policy and promote SM103 attention seeds CLA Signed This label is managed by the Meta Open Source bot.
#3416 opened Aug 19, 2026 by choijon5 Contributor Loading…
[testing] Skip pretuned scaled_mm when config exceeds device shared memory; add sm121 heuristic CLA Signed This label is managed by the Meta Open Source bot.
#3415 opened Aug 18, 2026 by yashb98 Loading…
2
[pallas] Enable DMA for tensor-core based indirect gathers CLA Signed This label is managed by the Meta Open Source bot.
#3414 opened Aug 18, 2026 by ethche Contributor Loading…
[pallas] Add pretuned jagged HSTU kernels for TPU CLA Signed This label is managed by the Meta Open Source bot.
#3413 opened Aug 18, 2026 by ethche Contributor Loading…
Stop the shared tile strategies and planner from assuming CuTe CLA Signed This label is managed by the Meta Open Source bot.
#3412 opened Aug 18, 2026 by aditvenk Contributor Loading…
[cute] Generalize tcgen05 fragment epilogues to thread-local transforms CLA Signed This label is managed by the Meta Open Source bot.
#3410 opened Aug 18, 2026 by ethche Contributor Loading…
2
[autotuner] extend the B200 matmul heuristic to multi-matmul kernels CLA Signed This label is managed by the Meta Open Source bot.
#3409 opened Aug 17, 2026 by calebmkim Contributor Loading…
[Pallas] Keep private remote-copy buffers in VMEM CLA Signed This label is managed by the Meta Open Source bot.
#3408 opened Aug 17, 2026 by AmesingFlank Contributor Loading…
[Pallas] Reuse aligned HBM windows as resident matmul Refs CLA Signed This label is managed by the Meta Open Source bot.
#3407 opened Aug 17, 2026 by AmesingFlank Contributor Loading…
[Pallas] Keep aligned static resident slices as Ref views CLA Signed This label is managed by the Meta Open Source bot.
#3406 opened Aug 17, 2026 by AmesingFlank Contributor Loading…
[Pallas] Drain computed-source sends after device loops CLA Signed This label is managed by the Meta Open Source bot.
#3405 opened Aug 17, 2026 by AmesingFlank Contributor Loading…
[Pallas] Stage aligned HBM windows on any tensor axis CLA Signed This label is managed by the Meta Open Source bot.
#3404 opened Aug 17, 2026 by AmesingFlank Contributor Loading…
[Pallas] Overlap read-only input DMAs with weight streams CLA Signed This label is managed by the Meta Open Source bot.
#3403 opened Aug 17, 2026 by AmesingFlank Contributor Loading…
[Pallas] Lower static advanced indices as basic slices CLA Signed This label is managed by the Meta Open Source bot.
#3402 opened Aug 17, 2026 by AmesingFlank Contributor Loading…
[Pallas] Preserve computed scalar indices across loop lowering CLA Signed This label is managed by the Meta Open Source bot.
#3401 opened Aug 17, 2026 by AmesingFlank Contributor Loading…
[Pallas] Pass TPU VMEM capacity to Mosaic CLA Signed This label is managed by the Meta Open Source bot.
#3400 opened Aug 17, 2026 by AmesingFlank Contributor Loading…
[Pallas] Hoist initial buffered DMAs over pure compute CLA Signed This label is managed by the Meta Open Source bot.
#3399 opened Aug 17, 2026 by AmesingFlank Contributor Loading…
[Pallas] Prove fixed scalar-derived loop extents CLA Signed This label is managed by the Meta Open Source bot.
#3398 opened Aug 17, 2026 by AmesingFlank Contributor Loading…
[Pallas] Refill single-buffer matmul windows after use CLA Signed This label is managed by the Meta Open Source bot.
#3397 opened Aug 17, 2026 by AmesingFlank Contributor Loading…
[Pallas] Drain looped remote receives after the loop CLA Signed This label is managed by the Meta Open Source bot.
#3396 opened Aug 17, 2026 by AmesingFlank Contributor Loading…
ProTip! Type g i on any issue or pull request to go back to the issue listing page.