github.com/llvm/torch-mlir issues | Ecosyste.ms: OpenCollective

[Bazel] Add SparseTensorDialect deps

sjain-stanford opened this pull request 8 months ago

link out of date

ai-mannamalai opened this issue 8 months ago

[Documentation] Show faster build command first in docs/development.md

renxida opened this pull request 8 months ago

[Stablehlo]index type use i64

Xinyu302 opened this pull request 8 months ago

[Torch] Decompose AtenMaskedScatterOp

Xinyu302 opened this pull request 8 months ago

Crash with TorchBackendToLinalgOnTensorsBackendPipeline

zjgarvey opened this issue 8 months ago

[ONNX][TorchToLinalg] Add support for dynamic dims in Interpolate lowering

zjgarvey opened this pull request 8 months ago

[Torch] Fix bugs for `Torch::AtenOneHotOp`

angelz913 opened this pull request 8 months ago

[FxImporter][TOSA] Enable FxImporter to TOSA e2e tests

sjarus opened this pull request 8 months ago

[Stablehlo] refactor amax, max, max.dim's lowering to stablehlo

qingyunqu opened this pull request 8 months ago

Don't fold `aten.clone` if result isn't same type as input

AaronStGeorge opened this pull request 8 months ago

Add support for left and right shift in the Tensor_Scalar case

KyleHerndon opened this pull request 8 months ago

[Torch] Fix AtenSliceTensorOp::fold

Xinyu302 opened this pull request 8 months ago

[torch-mlir][sparse] sparse diagonal feature scaling test

aartbik opened this pull request 9 months ago

Replace some depreciated uses of cast

zjgarvey opened this pull request 9 months ago

Implement `onnx.Hardmax` lowering

lialan opened this pull request 9 months ago

[TorchToLinalg] add support for quantized group conv

zjgarvey opened this pull request 9 months ago

build: manually update PyTorch version

vivekkhandelwal1 opened this pull request 9 months ago

[Torch] Fix PrimNumToTensorScalarOp::fold

Xinyu302 opened this pull request 9 months ago

[stablehlo] verify stablehlo backend contract

penguin-wwy opened this pull request 9 months ago

[sparse] convert to sparse before any use in sparse test.

PeimingLiu opened this pull request 9 months ago

[torch-mlir][sparse] enable test on ReLu

aartbik opened this pull request 9 months ago

[torch-mlir] bump to llvm@70e227a404e51f9248c7ad5d79953805b2afacb4

aartbik opened this pull request 9 months ago

[ONNX] Fix bugs for the `onnx.OneHot` operator

angelz913 opened this pull request 9 months ago

[ONNX] Fix incorrect result type for `onnx.OneHot` operator

angelz913 opened this pull request 9 months ago

Expands Q Commuting Ops

zjgarvey opened this pull request 9 months ago

[FxImporter] Add an e2e test example for FxImporter

penguin-wwy opened this pull request 9 months ago

[Torch] eliminate "getWithLeastStaticInformation" in DecomposeAtenTriuOp

Xinyu302 opened this pull request 9 months ago

[Stablehlo] fix aten.randn's lowering with f32 element type

qingyunqu opened this pull request 9 months ago

[Stablehlo] lowering aten.randn & aten.normal_functional to mhlo.rng …

qingyunqu opened this pull request 9 months ago

Generalize Operand Quantization in FuseQuantizeOps

zjgarvey opened this pull request 9 months ago

[ONNX] Handle one-input case for `onnx.Min` operator

angelz913 opened this pull request 9 months ago

[ONNX] Handle one-input case for `onnx.Max` operator

angelz913 opened this pull request 9 months ago

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

mgehre-amd opened this issue 9 months ago

[NFC] Delete the deprecated example cases

penguin-wwy opened this pull request 9 months ago

[stablehlo] support dynamic-shaped index in stablehlo conversion for aten.index-like ops

Vremold opened this pull request 9 months ago

[NFC] Standardize the std::is_same competime expression

penguin-wwy opened this pull request 9 months ago

[onnx][torch-mlir][linalg] Gridsampler addition of nearest mode

afalkenberg1 opened this pull request 9 months ago

[linalg] Implement strict mode lowering for aten.view.

stellaraccident opened this pull request 9 months ago

[sparse] propagate sparsity properly when decompose torch operations.

PeimingLiu opened this pull request 9 months ago

Updates Onnx Version to 1.16

zjgarvey opened this pull request 9 months ago

Add support for the onnx.SequenceConstruct op.

AWoloszyn opened this pull request 9 months ago

[sparse] match fx node using target name instead of variables name

PeimingLiu opened this pull request 9 months ago

Update development.md

angelz913 opened this pull request 9 months ago

WIP: [torch-mlir][sparse] enable sparsity INTO network

aartbik opened this pull request 9 months ago

Include Shape Information Into DecomposeComplexOps Patterns

zjgarvey opened this issue 9 months ago

[torch-mlir][sparse] minor tweaks in sparse tests

aartbik opened this pull request 9 months ago

Update version pin to onnx 1.16

stellaraccident opened this issue 9 months ago

[FxImporter] Eliminate the dependency on the refinement pass

penguin-wwy opened this pull request 9 months ago

[torch-mlir][sparse] recognize to_dense primitive

aartbik opened this pull request 9 months ago

[Stablehlo] fix lowering gelu(x, tanh)

qingyunqu opened this pull request 9 months ago

[Linalg] [Stablehlo] Promote type for compare scalar op

penguin-wwy opened this pull request 9 months ago

[torch-mlir][sparse] add a true network to our NN tests

aartbik opened this pull request 9 months ago

[torch-mlir][sparse] test for sparse "activation"

aartbik opened this pull request 9 months ago

[sparse] fix double free due to incompatibility between buffer-deallo…

PeimingLiu opened this pull request 9 months ago

[ONNX] Reduces Transpose Opset Version

zjgarvey opened this pull request 9 months ago

Temporarily remove QuantizedMLP_basic

zjgarvey opened this pull request 9 months ago

Integrate llvm-project at dabdec1001dc368373dd581cf72f37a440873ce3

bjacob opened this pull request 9 months ago

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

bjacob opened this issue 9 months ago

QuantizedMLP currently failing in CI

zjgarvey opened this issue 9 months ago

[torch-mlir][sparse] add simple sparsity "propagation" rules

aartbik opened this pull request 9 months ago

TestCI

penguin-wwy opened this pull request 9 months ago

MaxPool1d lowering to linalg

NeverRaR opened this pull request 9 months ago

[Linalg] Refactor compare scalar op

penguin-wwy opened this pull request 9 months ago

boolean indexing ops: AtenNonzeroOp, AtenIndexTensorOp, AtenMaskedSelectOp

renxida opened this issue 9 months ago

[Stablehlo] enable Stablehlo refbackend with Interpreter

qingyunqu opened this pull request 9 months ago

build: manually update PyTorch version

vivekkhandelwal1 opened this pull request 9 months ago

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

mgehre-amd opened this issue 9 months ago

Revert "Decompose AtenNonzeroOp"

vivekkhandelwal1 opened this pull request 9 months ago

[FxImporter] Add backend lowering to Fx API

penguin-wwy opened this pull request 9 months ago

[Torch]Emit AtenDetach_Op

Xinyu302 opened this pull request 9 months ago

[Torch]Support conv_transpose1d and conv_transpose3d

Xinyu302 opened this pull request 9 months ago

[Stablehlo] Bump stablehlo to ab92adeda9119a6c3914cd42367b0a2b70765e91

qingyunqu opened this pull request 9 months ago

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

trirpi opened this issue 9 months ago

[torch] Add OnnxToTorch lowering for `onnx.HammingWindow`

vinayakdsci opened this pull request 9 months ago

[torch-mlir] Bump LLVM to llvm/llvm-project@fc83eda4

aartbik opened this pull request 9 months ago

Decompose AtenNonzeroOp

renxida opened this pull request 9 months ago

[ONNX] Enables data propogation for onnx shape inference

zjgarvey opened this pull request 9 months ago

Bump llvm version to 97069a86193a617a9e4cf742a29db6116b2bf449

jpienaar opened this pull request 9 months ago

[ONNX] Add OnnxToTorch lowering for SoftmaxCrossEntropyLoss op

vivekkhandelwal1 opened this pull request 9 months ago

[torch] Add Canonicalize Pattern for embedding op

pashu123 opened this pull request 9 months ago

[torch] Add OnnxToTorch lowering for `onnx.HannWindow`

vinayakdsci opened this pull request 9 months ago

Revert Onnx.Selu lowering to corresponding Aten op

vivekkhandelwal1 opened this pull request 9 months ago

update the path of submodules

Jason048 opened this pull request 9 months ago

Revert "[ONNX] Fix Onnx.Selu lowering and canonicalizer for IntImplicit op (#3221)"

rsuderman opened this pull request 9 months ago

Folder and Canonicalizer for PrimsConvertElementTypeOp and AtenMaxPool2dWithIndicesOp

zezhang opened this pull request 9 months ago

Revert hyperbolic trigonometric decompositions

rsuderman opened this pull request 9 months ago

(WIP) fix lt for tensor arg

dan-garvey opened this pull request 9 months ago

[linalg] Fix bug for conversion of complex dtype

pashu123 opened this pull request 9 months ago

[Torch] Emit ChannelshuffleOp and decompose it.

Xinyu302 opened this pull request 9 months ago

iree-compiler failed to compile gpt2

Peter9606 opened this issue 9 months ago

[Release Builds] Use `-no-build-isolation` to decouple from `pyproject.toml`

sjain-stanford opened this pull request 9 months ago

[torch-mlir][sparse] add a few missing passes to the ref pipeline

aartbik opened this pull request 9 months ago

Fix onnx atanh lowering

jinchen62 opened this pull request 9 months ago

Fix onnx asinh lowering

jinchen62 opened this pull request 9 months ago

Fix onnx acosh lowering

jinchen62 opened this pull request 9 months ago

Re-enable LTC Build

antoniojkim opened this pull request 9 months ago

Integrate LLVM at llvm/llvm-project@593f6fdcb4bb3ff81ba4e6f89d7b16540c4b9eaf

rsuderman opened this pull request 9 months ago

[Stablehlo] Improve the lowering of pool op in stablehlo

Xinyu302 opened this pull request 9 months ago

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

sjain-stanford opened this issue 9 months ago