Skip to content

Pull requests: llvm/torch-mlir

New pull request New
190 Open 3,548 Closed
190 Open 3,548 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

[TorchToTosa] Lower conv1d via fake rank-4 conv2d
#4626 opened Jun 30, 2026 by jackv1ck Contributor Loading…
[TORCH] Add support for aten.absolute op via torch decomposition
#4624 opened Jun 29, 2026 by AiyyappanMR Loading…
3
[TorchToLinalg] Fix depthwise conv_transpose2d collapse_shape error
#4621 opened Jun 24, 2026 by faresernez Loading…
5
fix: break circular dependency to enable 'BUILD_SHARED_LIBS'
#4620 opened Jun 23, 2026 by jackfiled Loading…
1
[Torch] Add aten.triplet_margin_loss decomposition
#4615 opened Jun 18, 2026 by alex1xu • Draft
[Torch] Add aten.smooth_l1_loss decomposition
#4614 opened Jun 18, 2026 by alex1xu • Draft
[Torch] Add aten.diag decomposition
#4613 opened Jun 18, 2026 by alex1xu • Draft
[Torch] Fix verifier crashes on malformed global slot initializer IR
#4612 opened Jun 17, 2026 by alex1xu Loading…
1
1
Milestone 1: First-class PT2E quantization support in torch-mlir
#4611 opened Jun 17, 2026 by sahas3 Member Loading…
4
[Bazel] Add Bazel rules for Python bindings
#4609 opened Jun 16, 2026 by kalvdans Loading…
[Torch] Lower AtenLogsumexpOp via exp/sum/log decomposition
#4606 opened Jun 16, 2026 by johnny19436 Loading…
1
23
[TorchToLinalg] Zero-extend unsigned operands in add/sub Tensor lowering
#4601 opened Jun 14, 2026 by javierdejesusda Loading…
[TorchToTosa] Lower MXFP4 aten._scaled_mm_v2 to TOSA
#4598 opened Jun 9, 2026 by manaalmj Collaborator Loading…
[DecomposeComplexOps] Fix zero-rank ellipsis in aten.einsum
#4594 opened Jun 7, 2026 by choi3171 Loading…
1
[TMTensor] Add lowering of attention with an explicit scale value
#4593 opened Jun 3, 2026 by AGindinson Contributor Loading…
2
Bump the github-actions group with 2 updates dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#4592 opened Jun 3, 2026 by dependabot Bot Loading…
[BAZEL] Replace WORKSPACE with MODULE to support Bazel 9
#4589 opened May 30, 2026 by shantanu-gontia Loading…
8
[TorchOnnx] Fix ScatterND last unflatten step
#4586 opened May 28, 2026 by juanigp Loading…
[TorchToTosa] Add lowering for AtenSortOp
#4581 opened May 26, 2026 by alosim01 Loading…
24
added lowering for torch._int_mm thereby supporting int8 matmul.
#4573 opened May 19, 2026 by NMJ0 Loading…
ci: declare workflow-level contents: read on 4 workflows
#4571 opened May 15, 2026 by arpitjain099 Loading…
[Torch] Support mask mod arguments in flex_attention HOP
#4570 opened May 13, 2026 by keshavvinayak01 Contributor Loading…
10
Lower aten.cumsum in TorchToLinalg
#4566 opened May 8, 2026 by KyleHerndon Contributor Loading…
Avoid inferred expand_shape in unflatten lowering
#4565 opened May 8, 2026 by KyleHerndon Contributor Loading…
DecomposeAtenAminAmaxOp negative axis fix
#4556 opened May 4, 2026 by voonter Loading…
1
1
ProTip! Follow long discussions with comments:>50.