Ecosyste.ms: OpenCollective

An open API service for software projects hosted on Open Collective.

github.com/llvm/torch-mlir

The Torch-MLIR project aims to provide first class support from the PyTorch ecosystem to the MLIR ecosystem.
https://github.com/llvm/torch-mlir

[Stablehlo] lowering aten.round to stablehlo.round_nearest_even (#3011)

ad6159c7cb6e5105827c99aa6bb2cbe01f7a36d5 authored 10 months ago by Yuanqiang Liu <[email protected]>
[torch] Update folders for splat operators (#3012)

Splat operators required the output is 1-D. This was not a required
restriction and was loosene...

e78c99e74e115b4733f06f2ed186f74514982f74 authored 10 months ago by Rob Suderman <[email protected]>
[TorchDynamo] Enable Elemtwise ops for Scalar arg (#2744)

This commit provides dummy solution to support elmentwise operations
(mul, add) with scalar arg...

4b1e87ce672a1f19ae04d2136fb83c93c95b545d authored 10 months ago by Devjiu <[email protected]>
[onnx] Fix onnx.ReduceMean lowering (#3002)

Reduce mean lowerings did not succesfully lower to `linalg` via torched.
There were two separat...

8fb28661f9168c7b76a691125d8ebdff1732f920 authored 10 months ago by Rob Suderman <[email protected]>
[Torch Dialect] emit aten::mul and add folder (#3007)

229ca3a9e1cf1fc24a45e29315fd6af41322dcd3 authored 10 months ago by Yuanqiang Liu <[email protected]>
[Torch Dialect] emit aten::warn (#3003)

* torch-mlir may not handle `aten.warn`. But it could be handled by
custom users' backend which...

a3fe130f73f160c4d5b984f8de5b26aa471cfc9a authored 10 months ago by Yuanqiang Liu <[email protected]>
[onnx] Fix expand operation for dynamic shape max (#3001)

If the broadcast shape is length-1 at a dim while `?` in the input dim
then we need to broadcas...

bd7f1baa42f55dbdc19dd3f88cbd44bce937928c authored 10 months ago by Rob Suderman <[email protected]>
[torch] Add folder for torch.aten.*.Scalar comparisons (#3000)

This folds small version of the tensor-scalar comparison operators as
they are commonly used fo...

07235849361e01152decd9471be0985c42b4a1f7 authored 10 months ago by Rob Suderman <[email protected]>
fximporter: support newer torch versions (#2999)

uses version checking since attributes exist in both versions, the only
thing that changes is w...

80c7bc3f7ae12413836a2f610a6491794b4dbb08 authored 10 months ago by Daniel Garvey <[email protected]>
Fix link to roadmap in README.md (#2995)

The file was renamed by PR https://github.com/llvm/torch-mlir/pull/2842.

6b3a7d07c2c76f5e8437ff4e88110899621557b9 authored 10 months ago by Dmitry Babokin <[email protected]>
[onnx] Add support for `onnx.Gemm` with no bias (#2993)

Previous gemm version required a bias vector.
This provides an alternate path to `Torch::AtenM...

551a4e45f36574b6f0bf892a2d67d877e0253441 authored 10 months ago by Andreas Falkenberg <[email protected]>
[onnx] Fix constant pad for dynamic shape (#2989)

The current padding operation was not functional for dynamic shapes.
Updated and enabled tests ...

1964208d19a296ce55d267b5f8a8895025cb09a3 authored 10 months ago by Rob Suderman <[email protected]>
[onnx] Handle optional arguments in Clip op pattern. (#2976)

Spec: https://onnx.ai/onnx/operators/onnx__Clip.html

7b18646defbe24653e041279ab4a772b757f6a23 authored 10 months ago by Scott Todd <[email protected]>
build: manually update PyTorch version (#2992)

Set PyTorch and TorchVision version to nightly release 2024-03-07.
This commit also removes the...

6e84752c395a828eb612b21be4ab26d9f7e60b22 authored 10 months ago by Vivek Khandelwal <[email protected]>
[doc] fix broken links in documents (#2990)

Co-authored-by: wenyangwang <[email protected]>

d5693b3f51a8414cddf4e486daff52d8fa87cfa5 authored 10 months ago by penguin_wwy <[email protected]>
[onnx] Adding lowering for `onnx.Size` operation (#2985)

We can support `onnx.Size` by requesing the size of each dimensions and
taking the product of t...

c15f1a2bd2276b2ed6e9b47fdb9b8f9b8da5b2dd authored 10 months ago by Rob Suderman <[email protected]>
[onnx] Migrate `onnx.ReduceMax` to match `onnx.ReduceMin` (#2981)

This mostly copy-pastes the reduce minimum implementation to reduce max
to improve test coverag...

a78659742a20d1d99cd71c860e212a9156f03a25 authored 10 months ago by Rob Suderman <[email protected]>
[onnx][torch] Gridsampler E2E test and corrections of gridsampler (#2987)

The addition of an e2e test is actually provided in the Shark-Testsuite.
This adds 2 test cases...

ea76dd12ba08abf3cdfa02b74f2d2bde37ab0529 authored 10 months ago by Andreas Falkenberg <[email protected]>
[torch] Rework `aten.repeat` to use flatten and unsqueeze (#2984)

Current implementation depends on using `aten.view` which has issues
inferring tensor collapse/...

06292d9429e4f0052fc0a15cc548b95acd154651 authored 10 months ago by Rob Suderman <[email protected]>
e2e support aten.linalg_norm to aten.linalg_vector_norm (#2953)

Add e2d support for `aten.linalg_norm` by decompose it to
`aten.linalg_vector_norm`.

Lowerin...

aa7c9a965342116f09d991e20c6d6335a673f729 authored 10 months ago by Ze Zhang <[email protected]>
[torch] Add support for `torch.split_with_sizes` via decompose (#2979)

Convert to individiual slices and tuple together as a list.

---------

Co-authored-by: Scot...

bc0527676b10f5e6d2d9a55b54ec150cdce2b226 authored 10 months ago by Rob Suderman <[email protected]>
[onnx] Add support for constants of `i1`s (#2978)

`getRawBuffer` expects a densely packed vector of `i1` values however
`onnx` does not densely p...

933db87a07fb828b17b75f2f5f396a434f8f1a17 authored 10 months ago by Rob Suderman <[email protected]>
[FxImporter] remove dataclass slots to support python3.9 (#2974)

* that `dataclass`'s `slots` is supported after python 3.10.

4d01b0f1a38708d6e7966d1df326dcc9e52d8c5e authored 10 months ago by Yuanqiang Liu <[email protected]>
[torch] Additional folders for shape computations (#2972)

A handful of operations are commonly used in shape calculations (slice,
concat, broadcast). Add...

a86e89ecb5c7929a39a38743fb7cacadf1ff41bb authored 10 months ago by Rob Suderman <[email protected]>
[MLIR][ONNX] Add ONNX ReduceProd support (#2943)

Alternatives to https://github.com/llvm/torch-mlir/pull/2908

Fix https://github.com/nod-ai/SH...

09875fabd1b37b8c15822088cebe57a6e866c528 authored 10 months ago by Chi_Liu <[email protected]>
[torch] Make torch.aten.unflatten lower directly to linalg (#2971)

Existing lowering via aten.view does not work as well for dynamic shapes
as the lowering to ten...

19d488827859d0a1611255e1b49666186aa0cd0f authored 10 months ago by Rob Suderman <[email protected]>
[onnx] Fix onnx.gather lowering for rank-0 indices (#2973)

We assumed rank was atleast 1 however it can be rank-0, generating an
illegal pair of flatten /...

d51e80b648cf114165a466a36b237dd5e2949009 authored 10 months ago by Rob Suderman <[email protected]>
[Stablehlo] add torch_to_stablehlo::getBackendTypeForScalarType (#2975)

916554f270bebcb8a2195ce58eea7dd2c04c47e1 authored 10 months ago by Yuanqiang Liu <[email protected]>
[torch] Add an `aten.cat` length-0 canonicalization (#2966)

If an input is length-0 along the dimension of canonicalization we can
remove the tensor from t...

61f0a5facf6d6bde55eecc4200d048aa55690b64 authored 10 months ago by Rob Suderman <[email protected]>
[torch] Support `aten.view` rank-0 collapse (#2965)

Collapsing to a rank-0 tensor using `aten.view` was currently bailing
out. Added the special case.

d030bffc624860b57d43dc918e3bd2a55d33e077 authored 10 months ago by Rob Suderman <[email protected]>
[onnx] Fix type on create_module() in onnx_importer.py. (#2968)

The type returned was changed in
https://github.com/llvm/torch-mlir/pull/2795. This led to erro...

e7d90a4b82be35ae7aed9bd801048205abe7de38 authored 10 months ago by Scott Todd <[email protected]>
[MLIR][TORCH] Fix OnnxToLinalg lowering issue for sub and sum op (#2954)

This commit adds the support for scalar conversion to byte.
This commit also fixes the OnnxToL...

579ac8b66628b5707ca1a7c4c41fbf4c829b30b5 authored 10 months ago by Vivek Khandelwal <[email protected]>
Implement lowering of torch.aten.fmod.Tensor (#2767)

Closing https://github.com/nod-ai/SHARK-Turbine/issues/351

76b81e0ccdefd05bd7d6026ee04c060e82b49751 authored 10 months ago by mmakevic <[email protected]>
[torch-mlir][sparse] fixed merge conflict (#2967)

f21b76b68a411819df0795a2fe483b8eeb40d0f0 authored 10 months ago by Aart Bik <[email protected]>
[torch-mlir][sparse] support e2e sparse kernels with COO inputs. (#2939)

e85a2a87c5662c26e047a2d93d3ff6216cabdcec authored 10 months ago by Peiming Liu <[email protected]>
Bump LLVM to llvm/llvm-project@e5ed7b6e2fd368b722b6359556cd0125881e7638 (#2964)

ed6e75908b959129c0abb571b849597a792f44bf authored 10 months ago by Rob Suderman <[email protected]>
[onnx][torch] Lower `onnx.grid_sampler` to the `torch` equivalents (#2952)

This is the lowering of gridsampler from onnx to torch using our prior
implementation of AtenGr...

5437f32193888f4cae3b4ae02123bd8828564ad6 authored 10 months ago by Andreas Falkenberg <[email protected]>
[onnx] Import `onnx` import to pass remaining tests (#2951)

Finish supporting importing the vast majority of `onnx` operations. This
includes:
- region su...

e48fe4588631e7a37a2899f9d4cd5c4cbc967481 authored 10 months ago by Rob Suderman <[email protected]>
[torch] Fix folders and `cat` and `view` torch lowerings (#2963)

A bunch of small fixes are interlinked and trigger crashes if not
addressed as a group. This in...

6f3d62ab04e91bbe67d51b3c0b467f12fc3ed870 authored 10 months ago by Rob Suderman <[email protected]>
[torch] Fix DecomposeAtenInstanceNorm decomposition (#2960)

The decomposition only suports a NCHW lowering however the operation can
support arbitrary spat...

73b6df9007d8691aca328e1f95991ffe9691ace4 authored 10 months ago by Rob Suderman <[email protected]>
[torch] Add edgecase for aten.shape_to_tensor for rank-0 input (#2962)

Currently lowering uses `tensor.from_elements` which does not allow zero
inputs. In this case w...

dd673cfa8de6f215e27eedca54e53fb2f114b65d authored 10 months ago by Rob Suderman <[email protected]>
[tosa] Fix TOSA batch matmul lowering to correct transpose ordering (#2959)

The corrective transpose at the end is computed incorrectly. Is it
actually computin the invers...

08bc013fcd3232cbf01ad029f057b2fc022e56e1 authored 10 months ago by Rob Suderman <[email protected]>
[onnx] Fix ReduceMean lowering to torch (#2956)

Torch lowering only supported the most recent version. Refactored the
lowering so more easily h...

4a7a7d76f8870cad43a1803312efce7a8ae8643b authored 10 months ago by Rob Suderman <[email protected]>
Add support for torch arange float module (#2749)

Added Support for float dtype in in torch.arange in TOSA Dialect

This resolves the following ...

d541779f3754471f95d8ece8daa63e959168e22f authored 10 months ago by Abhishek-TyRnT <[email protected]>
[torch-mlir][sparse] add JIT test for block sparse SpMV (#2955)

This required adding a "decompose" pass to the torch lowering, since
torch.mv was not directly ...

30212547a9d750d6406383f6c706e6eae3395e37 authored 10 months ago by Aart Bik <[email protected]>
[torch] Rework lowering to tm_tensor.scatter to stop serialization (#2940)

We collapsed and broadcasted scatter indices to a single element
version. We should instead upp...

e30a083affb65c301066eda3df7112c06f4291da authored 10 months ago by Rob Suderman <[email protected]>
[MLIR][TORCH] Add support for tanh approximation for Gelu op (#2941)

Fixes https://github.com/nod-ai/SHARK-Turbine/issues/461

Signed-Off By: Vivek Khandelwal <viv...

d628b5fd060eaff4c9ae858fa5fe79356b4018fa authored 10 months ago by Vivek Khandelwal <[email protected]>
[MLIR][TORCH] Extend support for OnnxToLinalg lowering for Dropout and Div op (#2938)

Fixes https://github.com/nod-ai/SHARK-Turbine/issues/451,
https://github.com/nod-ai/SHARK-Turbi...

d81747eadbbdc0f97b64dd2964aedb6497de4435 authored 10 months ago by Vivek Khandelwal <[email protected]>
Expose `func_name` to the main fx import API (#2949)

As titled.

3cbe6c98ec9a67964ecb5947f7664e34e9ba4b5b authored 10 months ago by Sambhav Jain <[email protected]>
Implement lowering of torch.aten.norm.Scalar (#2899)

Closes
[nod-ai/SHARK-Turbine#365](https://github.com/nod-ai/SHARK-Turbine/issues/365)

c5a1da1910f8e1a5dac748eb2806833bd4f1b0c2 authored 10 months ago by ptrifunovic98 <[email protected]>
Make a typing dependency that is not in older PyTorch backwards compatible. (#2948)

This was found in a downstream that is pegged to an older PyTorch
version.

89e02c195b910621246c55003fca86558162c6da authored 10 months ago by Stella Laurenzo <[email protected]>
[ci] Fix mpmath 1.4.0 error by forcing 1.3.0 (#2946)

`mpmath 1.4.0` changes some import locations breaking `torch`. Changing
to `1.3.0` to avoid bre...

ec2b80b433c9a1b56352f9851d5258218f8740ab authored 10 months ago by Rob Suderman <[email protected]>
[torch-mlir][sparse] add block sparsity to mlir lowering (#2942)

Also note that we are in the process of proposing SparseTensorMetadata
to PyTorch FX graph expo...

4147b280cef981e53dfaa171572cf783c0fe37c2 authored 10 months ago by Aart Bik <[email protected]>
[torch] GridSample TorchToLinalg lowering (#2883)

Lowers `torch.grid_sample` to the equilvalent `linalg` representation.

55dc8deb9221c9ec0fe2a991542f2f788c62a3e1 authored 10 months ago by Andreas Falkenberg <[email protected]>
build: manually update PyTorch version (#2933)

Set PyTorch and TorchVision version to nightly release 2024-02-20.

Signed-Off By: Vivek Khand...

5af249566b85a97e5c96c847877e4fc9fda57ec1 authored 10 months ago by Vivek Khandelwal <[email protected]>
[onnx] Drop `ConstantOfShape` logic form importer, fix torch lowering (#2930)

There is no reason to treat `ConstantOfShape` as a specialized import
any as there exists a onn...

53f6d06ab8ae619fdeecabaa0e25f7b621598ae8 authored 10 months ago by Rob Suderman <[email protected]>
[torch] Fixed edge conditions for strided slicing (#2929)

Strided slicing can occur with a negative stride. In these cases we need
to bound end different...

df2aa1a3699cbb161c0f6c0b475dee5ca8dab98d authored 10 months ago by Rob Suderman <[email protected]>
allow tosa.cast to convert from f32 to f16 (#2934)

According to the [official TOSA
spec](https://www.mlplatform.org/tosa/tosa_spec.html#_cast), `t...

0f80e75c2eb6dfed00bf051644a5e3fb97207bb8 authored 10 months ago by Srinath Avadhanula <[email protected]>
[torch-mlir][NFC] remove trailing whitespace (#2936)

534b266f2d198d2b6b2ed62d5b31f82d0e3d9f3c authored 10 months ago by Aart Bik <[email protected]>
[onnx] Enable crashing tests (#2928)

Crashing tests no longer crash, enable as either passing or xfail tests.

Co-authored-by: Xida...

13113df33e53a1d0dd7a1f2313ec101df142a152 authored 10 months ago by Rob Suderman <[email protected]>
[onnx] Update the importer to create a `none` for missing operands (#2931)

Some operands are optional so we require a placeholder for missing
operands. We invent an `onnx...

13553d49c9488e09fec6ba790fb095eea66c48ea authored 10 months ago by Rob Suderman <[email protected]>
Migrate passes in TorchConversion to use FunctionOpInterface. (#2935)

This enables better re-use in downstreams which use different func
implementations and should h...

4446fa00d8258311867496fc79d0b1dddd22a972 authored 10 months ago by Stella Laurenzo <[email protected]>
[torch] Add folder for `prim.NumToTensor.Scalar` (#2921)

Useful for `slice` lowerings that depend on tensors made form scalars.

135c81a4165f9e4c9070d72c485efece887d64f8 authored 10 months ago by Rob Suderman <[email protected]>
[torch] Folders for `torch.aten.*.tensor` operators [add, sub, mul] (#2878)

Simple folder for limited size aten tensor operations. This is primarily
useful for shape compu...

e80054a3cca385bf50760ad43a6d8e8bb799001d authored 10 months ago by Rob Suderman <[email protected]>
[onnx] Simplify onnx.slice lowering (#2919)

Onnx slice lowering used arange needlessly instead of directly
constructing the constant dimens...

cea51897a5255363f5f09dcb91433dfc11492598 authored 10 months ago by Rob Suderman <[email protected]>
[torch] Support dynamic step size for `torch.slice` (#2922)

For some reason we did not directly use the step size dynamically
despite its constructed using...

fd08578bdb24e0b2a3c85c907b766c972509b634 authored 10 months ago by Rob Suderman <[email protected]>
OnnxToTorch support for onnx.InstanceNormalization op (#2710)

https://github.com/nod-ai/SHARK-Turbine/issues/327

d29157b33fb66a6ef37971452cc6f8399bfbf374 authored 10 months ago by aldesilv <[email protected]>
[torch-mlir][sparse] inline sparse helper methods (#2918)

Even though the reference compiler is not about performance, inlining
the generated sparse help...

78e10ff09b78ba14c4c97100360205550c36669e authored 10 months ago by Aart Bik <[email protected]>
[onnx] Fix `onnx.sigmoid` for integer inputs/outputs (#2914)

Sample compilation crashes due to sigmoid with integer inputs/outputs.
This fix avoids crashing...

d65925a8b465d4a84be947d37197178d5c5cc6d2 authored 10 months ago by Rob Suderman <[email protected]>
[onnx] Fix onnx.gather lowering to use torch.aten.index_select (#2913)

Onnx's gather maps directly to `torch.aten.index_select`. We should just
use that path.

7a0d0e954b145d28c6e495b5324d11cb03402f60 authored 10 months ago by Rob Suderman <[email protected]>
[onnx] Fix crash when negative transpose values exist (#2915)

We are crashing due to indexing into a negative shape. Updated the
lowering to avoid the crash.

468c5339424e0f42d474106943c750de5519ff4d authored 10 months ago by Rob Suderman <[email protected]>
[torch-mlir][sparse][NFC] fixed typo (#2917)

grammar police

c5d8c12469d7b7badd35369106c4b975f718536c authored 10 months ago by Aart Bik <[email protected]>
[fx] Support mutation in ExportedProgram. (#2916)

As of https://github.com/pytorch/pytorch/pull/118969, `ExportedProgram`
has the long awaited fi...

5253282c55546d19e00f8b244c2da74cf76c8486 authored 10 months ago by Stella Laurenzo <[email protected]>
[onnx] Add testing using the `onnx` compilation using torch tests (#2795)

We can route the torch tests via `onnx` using the `torch.onnx.export`
tooling. We can then reim...

074f112d6afbfe48441083fa0e9764114d3c72de authored 10 months ago by Rob Suderman <[email protected]>
[bazel] commit after run buildifier (#2912)

49f63df0689a2c3351f051801bdd24833daa9a91 authored 10 months ago by Yuanqiang Liu <[email protected]>
[bazel] fix bazel with stablehlo refbackend and fix some typo (#2911)

5733c84443ed2ee3b0cbb75a9e425aa076c457a9 authored 10 months ago by Yuanqiang Liu <[email protected]>
[Stablehlo] add refbackend (#2712)

f3e8199a6d2871312619608b839ccd8037b12264 authored 10 months ago by Yuanqiang Liu <[email protected]>
add support for decomposition (#2879)

This commit adds decomposition support into the core aten operators
before importing the module...

8e2e5eeae991c825496e22470e3d3fb766d54a66 authored 10 months ago by saienduri <[email protected]>
DecomposeComplexOps: update parseEquation to skip space char for AtenEinsumOp op (#2910)

Just a minor update to skip the space char if included in the equation
string

---------

C...

f3b38e5d1214afa6046ad21543ab3bb10d2d3b98 authored 10 months ago by Ze Zhang <[email protected]>
Add support for bfloat16 in fximporter (#2896)

this introduces an additional soft dependency on the python ml_dtypes
python packages in order ...

77b7550997e91f19f27af085f8ae531e696e6406 authored 10 months ago by Daniel Garvey <[email protected]>
Bump torch to pytorch/pytorch@b51e024 (#2909)

This version of pytorch includes a patch to enable dynamo support on
Windows, so I would like t...

e7a09440d380827e90b94ef33bd82f32fda8874a authored 10 months ago by Ean Garvey <[email protected]>
[MLIR][Torch] Add OnnxToTorch and TorchToLinalg support for trig ops (#2903)

This commit adds the OnnxToTorch lowering for cosh, acosh, asin, asinh,
and atanh op.
This com...

d6d1a173dcebd7c0d62863673c4aee08a0c3853b authored 10 months ago by Vivek Khandelwal <[email protected]>
[torch] Fix tm_tensor.attention for end-to-end (#2907)

Some operations include a backend matcher for specialized operations. We
map these back to gene...

e9cdd6cbc558880da2b6faa70b6c844bd7b5f494 authored 10 months ago by Rob Suderman <[email protected]>
Drop torch attributes at the end of backend conversion. (#2876)

Fixes https://github.com/llvm/torch-mlir/issues/2866

Some backends / downstream projects expe...

d6e1d836ca8d49da25ad5e2f10d6816bfbb6ba2f authored 10 months ago by Scott Todd <[email protected]>
[torch-mlir][sparse] add JIT test to expose pending issues (#2906)

This test exposes issues that need fixing
(1) propagate sparsity into the FX graph (over elt-wi...

24c2fc0b5f90d870cbfd967c81460bcc5686d24d authored 10 months ago by Aart Bik <[email protected]>
[fx_importer] Convert non-persistent buffers lifted as tensor constants (#2902)

The investigation is largely recorded in
https://github.com/llvm/torch-mlir/pull/2881, but this...

3e836d8dad551b6e5302de1b84840b90ee039c83 authored 10 months ago by Sambhav Jain <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for Mean, IsInf, IsNaN, PRelu op (#2801)

This commit adds the OnnxToTorch support for Mean, IsInf, IsNaN, and
PRelu ops. All high priori...

9b967f6b5ab49b344af9a2c56659784502f2c488 authored 10 months ago by saienduri <[email protected]>
[torch-mlir][sparse] sparsity metadata refinement (#2901)

Various improvements on sparsity metadata:

(1) define single data structure for all sparsity ...

b6f4ca512ea93eaa34aad7b16a2bf6ff8d01350b authored 10 months ago by Aart Bik <[email protected]>
build: find Protobuf using config mode search (#2900)

This patch makes the Protobuf package mandatory in addition to forcing a
config mode search. T...

370d6ac9a2f723de7c7609d4128e58ac6d363b00 authored 10 months ago by Ashay Rane <[email protected]>
[torch-mlir][sparse] implement first sparse_jit end-to-end path (#2894)

This PR introduces a sparse_jit wrapper that can run simple models with
sparse tensor inputs en...

be8375d35037ca4ca496d0de4052745f5472277b authored 10 months ago by Aart Bik <[email protected]>
Fix test_add_uint8 failure to lower to linalg (#2893)

By updating convertScalarToDtype invocation pass original source and
destination datatypes for ...

bfb93cb99f259a614b4be7f6a4d04f6a07e4d395 authored 10 months ago by Xida Ren (Cedar) <[email protected]>
Bump stablehlo to openxla/stablehlo@e191eb4c3c3f3144503a8a117d760de5d… (#2891)

…dcc7e89.
* to involve `chlo-legalize-to-stablehlo` pass.

b8c48cf283c076c0b55998702ea380d74c1322a8 authored 11 months ago by Yuanqiang Liu <[email protected]>
[torch] Add `torch.aten.eq.Tensor` comparison folder (#2889)

Added a folded for a equals operator. This allows an equivalent
comparison folder, primarily fo...

c0f139be0f8371569c38b45ab2c925deb16292d2 authored 11 months ago by Rob Suderman <[email protected]>
Bump LLVM to llvm/llvm-project@bb180856ec28efe305dc77ca4bb3db12d8932edf (#2895)

Includes some minor first for `AffineMap::inferFromExprList`

d83b576c6e15cf7ebeefc1dbd65fd9061227c278 authored 11 months ago by Rob Suderman <[email protected]>
[torch] Folder for torch.aten.select.int for splat cases (#2890)

If the input or result is a splat value we can just constant fold the
result. This is common fo...

7d33ba69ac71981fb39f839d698300bcecf5353a authored 11 months ago by Rob Suderman <[email protected]>
Implement trace (#2790)

The lowering decomposes AtenTraceOp into an AtenDiagonalOp followed by
AtenSumOp.

The progre...

4cc62aeb24e28b3ff60df6ff4a0fd97cc045efc1 authored 11 months ago by Franz Haniel <[email protected]>
Add lowering support for math::AbsIOp (#2875)

There is no lowering support for math::AbsIOp, so if the operand is an
integer type, it will fa...

9659a436d1374612d7d2c7518a74dfd9ae821bc0 authored 11 months ago by Avinash Sharma <[email protected]>
[torch-mlir][sparse] add sparsification to linalg reference backend (#2887)

This adds a few passes that will ensure linalg with sparse tensors are
properly lowered to loop...

44f8f8982687564924379f5fc9f197f767f421bf authored 11 months ago by Aart Bik <[email protected]>
onnx: fix checks in TorchOnnxToTorch pass to match the ONNX spec (#2848)

This PR contains three commits to update the validation checks in the
ONNX -> Torch conversion ...

21f070e95fd219a01ac663c697f0d36c1fa279e8 authored 11 months ago by Ashay Rane <[email protected]>
[MLIR][TORCH] Modify Onnx.Reshape lowering for static shape cases (#2852)

This commit modifies the OnnxToTorch lowering of Onnx.Reshape op by
creating the result shape l...

4df96616dba72400071535c75188d94df7e44184 authored 11 months ago by Vivek Khandelwal <[email protected]>