Skip to content

Pull requests: llvm/torch-mlir

New pull request New
181 Open 3,477 Closed
181 Open 3,477 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

Use llvm::numbers instead of cmath constants
#4530 opened Apr 9, 2026 by annop-w Contributor Loading…
[Torch] Add PrimsProdOp with shape, dtype, and linalg lowering
#4526 opened Apr 8, 2026 by rsuderman Contributor Loading…
9
[TMTensor] Add is_causal attribute to aid mask dematerialisation.
#4520 opened Apr 2, 2026 by keshavvinayak01 Contributor Loading…
Bump the github-actions group across 1 directory with 5 updates dependencies Pull requests that update a dependency file github_actions Pull requests that update GitHub Actions code
#4519 opened Apr 2, 2026 by dependabot bot Loading…
Cache torch_mlir Prefix as CMake Variable
#4518 opened Mar 30, 2026 by sgjzfzzf Loading…
2
[TorchToTosa] Add lowering for aten.atan
#4517 opened Mar 29, 2026 by ahagro01 Loading…
[tosa] Update torch.aten.upsample_nearest2d legalization to use tosa.resize
#4516 opened Mar 27, 2026 by Tessil Contributor Loading…
[onnx_c_importer] Verify checksum for ONNX external tensor data
#4514 opened Mar 25, 2026 by 3em0 Loading…
4 tasks
[ScalarizeShapes] Fold select.int through cat in shape computations
#4513 opened Mar 24, 2026 by jtuyls Contributor Loading…
[Windows] Use math extras instead of M_PI
#4512 opened Mar 23, 2026 by zjgarvey Collaborator • Draft
2
[Torch] Roll pytorch
#4511 opened Mar 23, 2026 by zjgarvey Collaborator • Draft
[bug] Fix decomposition logic for logaddexp
#4509 opened Mar 22, 2026 by vihangm Loading…
1
[TorchOnnxToTorch] Add block_size support for onnx.DequantizeLinear
#4505 opened Mar 18, 2026 by jtuyls Contributor Loading…
11
build: fix installation failures of dependencies for macOS
#4504 opened Mar 17, 2026 by felixtensor Loading…
[torch] Add decomposition for aten._foreach_lerp.List
#4502 opened Mar 12, 2026 by BruceXinXin Contributor Loading…
[TorchToStablehlo] Add lowering for prims.xor_sum to stablehlo.reduce…
#4501 opened Mar 12, 2026 by BruceXinXin Contributor Loading…
[TorchOnnxToTorch] Fix LayerNormalization scale/bias dtype mismatch with stash_type
#4498 opened Mar 11, 2026 by bjw-0 Loading…
1
2
[TorchToStableHLO] Support bitwise_or.Scalar and bitwise_xor.Scalar l…
#4496 opened Mar 10, 2026 by BruceXinXin Contributor Loading…
1
[TorchToTosa] add conv reshape in core lowering
#4494 opened Mar 9, 2026 by catcor01 Contributor Loading…
47
Add negative PY_BUILTIN_TO_TORCH_OP
#4488 opened Mar 5, 2026 by DavidGinten Loading…
[Torch] Fix batch norm decomposition dtype for mixed-precision inputs
#4483 opened Mar 3, 2026 by rkayaith Member • Draft
2
Add decomposition for aten.miopen_batch_norm
#4482 opened Mar 3, 2026 by rkayaith Member Loading…
1
1
[TorchToTMTenor] enable broadcasting query- and key_seq_len of attention mask
#4464 opened Feb 8, 2026 by ziereis Loading…
3
[TorchToLinalg] Fix i8 scalar dtype conversion by passing dstOriginalDtype
#4454 opened Feb 2, 2026 by snarang181 Loading…
[TorchToStableHLO] Add pdist_forward and cdist_forward StableHLO lowe…
#4449 opened Jan 27, 2026 by andrewd-aws Loading…
ProTip! Exclude everything labeled bug with -label:bug.