Skip to content

Pull requests: pytorch/helion

New pull request New
70 Open 1,450 Closed
70 Open 1,450 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

[cutedsl] Fix packed-RHS lowering and add general stack/reshape views CLA Signed This label is managed by the Meta Open Source bot.
#1784 opened Mar 22, 2026 by jansel Loading…
[cutedsl] Fix broadcast and reshape-backed matmul lowering CLA Signed This label is managed by the Meta Open Source bot.
#1783 opened Mar 22, 2026 by jansel Loading…
[cutedsl] tcgen05 MMA support CLA Signed This label is managed by the Meta Open Source bot.
#1777 opened Mar 21, 2026 by jansel Loading…
Fix device sync in generic benchmarking functions for TPU/Pallas CLA Signed This label is managed by the Meta Open Source bot.
#1773 opened Mar 21, 2026 by norx1991 Loading…
2
restrict to persistent pid for dist kernels CLA Signed This label is managed by the Meta Open Source bot.
#1772 opened Mar 21, 2026 by shunting314 Loading…
1
move distributed runtime utils out of examples/ folder CLA Signed This label is managed by the Meta Open Source bot.
#1771 opened Mar 20, 2026 by shunting314 Loading…
avoid matching against class name in default_autotuner_fn CLA Signed This label is managed by the Meta Open Source bot.
#1770 opened Mar 20, 2026 by shunting314 Loading…
1
Support block_ptr/TensorDescriptor with extra_mask for loads CLA Signed This label is managed by the Meta Open Source bot.
#1768 opened Mar 20, 2026 by hinriksnaer Loading…
2
[WIP] Enable launch grid fission CLA Signed This label is managed by the Meta Open Source bot.
#1767 opened Mar 20, 2026 by bringlein • Draft
1
Removing skips and in some cases adding skipIfNotCUDA for cuda only features. CLA Signed This label is managed by the Meta Open Source bot.
#1766 opened Mar 20, 2026 by umechand-amd • Draft
[metal] Support elementwise kernels with >1D tensors CLA Signed This label is managed by the Meta Open Source bot.
#1765 opened Mar 20, 2026 by aditvenk • Draft
5
[metal] MslAstWalker + MetalBackend MSL codegen + device function hook + tests CLA Signed This label is managed by the Meta Open Source bot.
#1764 opened Mar 20, 2026 by aditvenk • Draft
[metal] Metal codegen for load/store/mask_to CLA Signed This label is managed by the Meta Open Source bot.
#1763 opened Mar 20, 2026 by aditvenk • Draft
1
increase signal pad size for dist matmul kernels CLA Signed This label is managed by the Meta Open Source bot.
#1753 opened Mar 20, 2026 by shunting314 Loading…
avoid nvshmem symm-mem backend CLA Signed This label is managed by the Meta Open Source bot.
#1750 opened Mar 19, 2026 by shunting314 Loading…
2
[WIP] Add reduction support to helion autodiff CLA Signed This label is managed by the Meta Open Source bot.
#1747 opened Mar 19, 2026 by karthickai • Draft
[Autotuner] Add generation_ctx() context manager for each autotuner generation CLA Signed This label is managed by the Meta Open Source bot.
#1745 opened Mar 19, 2026 by yf225 Loading…
1 task done
3
add kernel-filter to select kernel for allreduce-rmsnorm CLA Signed This label is managed by the Meta Open Source bot.
#1744 opened Mar 19, 2026 by shunting314 Loading…
more APIs to debug distributed kernel CLA Signed This label is managed by the Meta Open Source bot.
#1743 opened Mar 19, 2026 by shunting314 Loading…
[Experiment] LLM-guided autotuner MVP CLA Signed This label is managed by the Meta Open Source bot.
#1729 opened Mar 17, 2026 by kitrakrev • Draft
1
[Helion + torch.compile] Enable torch.compile fusion tests CLA Signed This label is managed by the Meta Open Source bot.
#1727 opened Mar 16, 2026 by yf225 Loading…
2
[Helion + torch.compile] Add store/load transform hooks and prologue/epilogue fusion codegen CLA Signed This label is managed by the Meta Open Source bot.
#1724 opened Mar 16, 2026 by yf225 Loading…
29
Add scheduled workflow to rerun GPU health check failures CLA Signed This label is managed by the Meta Open Source bot.
#1683 opened Mar 14, 2026 by v0i0 Loading…
Fix #934: Add setting to disable 0/1 specialization CLA Signed This label is managed by the Meta Open Source bot.
#1678 opened Mar 13, 2026 by tianrengao • Draft
1
2
Increasing block size dimensions to avoid configs which are slow and poor candidates. CLA Signed This label is managed by the Meta Open Source bot.
#1677 opened Mar 13, 2026 by umechand-amd Loading…
4
ProTip! Mix and match filters to narrow down what you’re looking for.