llvm/torch-mlir

Issues

• [ONNX] Add support for onnx.Resize with nearest_mode "round_prefer_floor" and "round_prefer_ceil"

  #3420 opened 6 days ago by flemairen6
  5

• Failed to lower "torch.aten.convolution" to linalg

  #3429 opened 4 days ago by josel-amd
  1

• Error lowering `index_put_`: 'tm_tensor.scatter' op mismatch in shape of indices and update value at dim#0

  #3433 opened 3 days ago by ScottTodd
  0

• Failed to lower 'torch.operator "onnx.AveragePool"' to torch

  #3428 opened 4 days ago by josel-amd
  1

• Failed to lower 'torch.operator "onnx.MaxPool"' to torch

  #3427 opened 4 days ago by josel-amd
  0

• Failed to lower 'torch.operator "onnx.MaxPool"' to torch

  #3422 opened 5 days ago by josel-amd
  0

• Failed to lower "torch.aten.sum.dim_IntList" to linalg

  #3423 opened 5 days ago by josel-amd
  0

• Re-enable the disabled sparse tests due to roll PyTorch

  #3418 opened 6 days ago by vivekkhandelwal1
  0

• Failed to lower torch.aten.slice.Tensor to linalg

  #3417 opened 7 days ago by josel-amd
  0

• [ONNX] Systematically expand ONNX functions before conversion to Torch to avoid needing bespoke conversions

  #3384 opened 19 days ago by andfau-amd
  11

• Crash with TorchBackendToLinalgOnTensorsBackendPipeline

  #3352 opened 7 days ago by zjgarvey
  0

• torchscript_stablehlo_backend_tinybert.py failed to lower Torch Backend IR -> StableHLO

  #3411 opened 8 days ago by FruitClover
  2

• Trying to lower elided IR from torch onnx to torch causes crash

  #3370 opened 9 days ago by renxida
  2

• onnx.MatMul version 1 not lowered (but it's essentially the same as version 13)

  #3324 opened 10 days ago by mgehre-amd
  0

• migrate to from member `x.cast<T>()` to `mlir::cast<T>(x)`

  #3299 opened 11 days ago by bjacob
  1

• [onnx] Attempting to lower onnx mlir with elided attributes causes crash

  #3394 opened 11 days ago by renxida
  7

• Some issues with migrating to one-shot-bufferize

  #3399 opened 11 days ago by zjgarvey
  11

• Include Shape Information Into DecomposeComplexOps Patterns

  #3312 opened a month ago by zjgarvey
  4

• unsupported aten.meshgrid operator

  #3366 opened 22 days ago by zhangdong-user
  0

• link out of date

  #3356 opened 25 days ago by ai-mannamalai
  0

• onnx.Transpose version 1 not lowered (but it's essentially the same as version 13)

  #3290 opened a month ago by mgehre-amd
  0

• Missing dtype support for OnnxToTorch

  #3255 opened a month ago by jinchen62
  3

• Update version pin to onnx 1.16

  #3310 opened a month ago by stellaraccident
  4

• [ONNX] Unsqueeze -> Torch -> Linalg issue

  #3101 opened a month ago by zjgarvey
  1

• QuantizedMLP currently failing in CI

  #3298 opened a month ago by zjgarvey
  0

• boolean indexing ops: AtenNonzeroOp, AtenIndexTensorOp, AtenMaskedSelectOp

  #3293 opened a month ago by renxida
  0

• `NotSupportedError` error when executing Readme example "TorchScript ResNet18"

  #3284 opened a month ago by trirpi
  0

• [ONNX] onnx.Loop

  #3136 opened 2 months ago by renxida
  5

• iree-compiler failed to compile gpt2

  #3267 opened a month ago by Peter9606
  0

• Strange issue related to `pyproject.toml` when building release wheels

  #3258 opened a month ago by sjain-stanford
  4

• Compilation of Quantized Model Failed

  #3220 opened 2 months ago by alexsifivetw
  1

• [ONNX] Dynamic size support for the onnx.GreaterOrEqual operator.

  #3129 opened 2 months ago by Peefy
  1

• `make_simple_dynamo_backend` does not work for single argument models.

  #3204 opened 2 months ago by ttrouwen-dmatrix
  2

• [ONNX] MatMulInteger Conversion Fails For Arg Rank != 2

  #3137 opened 2 months ago by zjgarvey
  2

• Build failed on x86 MacOS

  #3191 opened 2 months ago by lifengxiang1025
  0

• [e2e testing] make e2e_testing/main.py print ir / more informative error messages

  #3172 opened 2 months ago by renxida
  0

• [TORCH] `AtenFloorDivideOp` truncates instead of flooring which doesn't match `torch.floor_divide()` .

  #3142 opened 2 months ago by IanWood1
  1

• [TORCH] add support for torch.aten.floor_divide.Scalar

  #3143 opened 2 months ago by IanWood1
  0

• Slice Folder Fails Result Type Match Assert

  #3153 opened 2 months ago by zjgarvey
  0

• [onnx][torch][linalg] Support of corner align mode for gridsampler

  #3157 opened 2 months ago by afalkenberg1
  0

• buildAndTest.yml lacking trigger causes a bunch of notifications

  #3144 opened 2 months ago by renxida
  1

• [BUG][MLIR][BERT] examples/torchscript_stablehlo_backend_tinybert.py

  #3148 opened 2 months ago by vasslavich
  0

• [RFC] Mixed Quantized Types in Matmul Not Supported

  #3090 opened 2 months ago by zjgarvey
  5

• [MLIR][TORCH] Onnx.MaxPool fails on dynamic sizes

  #3135 opened 2 months ago by IanWood1
  0

• Out of tree build in conda environment / overdependency problem

  #3104 opened 2 months ago by ZzEeKkAa
  5

• LTC build error after PT bump: multiple definition of `torch::lazy::compute_shape_arange`

  #3120 opened 2 months ago by sjain-stanford
  1

• FX Importer error: `Could not deduce type from value info: tensor_meta=None, val=s0, sparsity=None`

  #3118 opened 2 months ago by sjain-stanford
  4

• Regression in onnx.PRelu

  #3092 opened 2 months ago by stellaraccident
  9

• torch_mlir.compile failing on RetinaNET

  #3096 opened 2 months ago by afanasyev-ilya
  0

• AtenSelectInt results in `failed to legalize operation 'arith.extui' that was explicitly marked illegal`

  #3077 opened 2 months ago by renxida
  1