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

[ONNX][TORCH-MLIR] LayerNorm (#2716)

Layer Normalization using the torch.aten.native_layer_norm

https://github.com/nod-ai/SHARK-T...

5862854bc8011a94a54edeb4fa278908e9eb2c2b authored 12 months ago by Andreas Falkenberg <[email protected]>
Implement aten.reflection_pad2d lowering to linalg

0860c41ee2a0bdec41f544f19eba170cf646c3ce authored 12 months ago by Frederik Harwath <[email protected]>
Minor typo fix: in not implemented message for the exclusive and reverse attributes for cumsum (#2740)

aee1fca2517b8bff3b18e3b01beaafe8d57a7dd8 authored 12 months ago by Xida Ren (Cedar) <[email protected]>
support for onnx.expand operator (#2729)

maps onnx.expand to torch aten broadcast_to, three tests added

---------

Co-authored-by: K...

29569713f3878226a6c1054a183dc227934dbe69 authored 12 months ago by kumardeepakamd <[email protected]>
build: manually update PyTorch version

Set PyTorch and TorchVision version to nightly release 2024-01-09.

Signed-Off By: Vivek Khandelw...

469c055190a042575a2259f8fe759da23963ce3f authored 12 months ago by Vivek Khandelwal <[email protected]>
[MLIR][ONNX] Add TorchToOnnx Support for DepthToSpace op

Signed-Off By: Vivek Khandelwal <[email protected]>

208ae355830707a0d1e85f05feca454ad2b346f0 authored 12 months ago by Vivek Khandelwal <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for Bernoulli and CastLike op

Signed-Off By: Vivek Khandelwal <[email protected]>

4707d3bdc6d7e1bb12b3e44dcf23455a7d445725 authored 12 months ago by Vivek Khandelwal <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for Dropout and Elu op

Signed-Off By: Vivek Khandelwal <[email protected]>

35e8f8679220a35dae4e49b988eeef5e47747f8c authored 12 months ago by Vivek Khandelwal <[email protected]>
[RFC] general support for Adaptive Pooling Ops (#2661)

Adaptive pooling ops can only be decomposed into their non-adaptive
counterparts in trivial cas...

07d0645f640bdc8b09a706150fa1a9a5f85b8147 authored 12 months ago by zjgarvey <[email protected]>
Fixing implicit double->float truncation warnings. (#2733)

Floating-point literals should use the correct type specifier.

4dd17f0b711523223e41606d9b7b6023b9149d46 authored 12 months ago by Ben Vanik <[email protected]>
[linalg] Added `aten.clamp` support with integers to `torch-to-linalg` (#2718)

The lowering for `aten.clamp` did not support integer types. Added
support for integer types in...

985e7796a4e4c2b939c4c350047db2473fcdc8f2 authored 12 months ago by Rob Suderman <[email protected]>
[OnnxToTorch] Delete unused variables. (#2728)

6096fcb347691982d721d74d96794ac0d17af0d9 authored 12 months ago by Han-Chung Wang <[email protected]>
Bump llvm-project to 6b65d79fbb4682468333cea42b62f15c2dffd8f3 (#2723)

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

fb1dfa31268c59a829ded35d304969c48ede388b authored 12 months ago by Kunwar Grover <[email protected]>
[torch-mlir] remove trailing whitespace from e2e test files (#2727)

aa7e95f7c8cde77528d273633baa8887f4795187 authored 12 months ago by Aart Bik <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for Slice Op (#2696)

4e5e34d215fa00912a8205a1d0406ee5719003a7 authored 12 months ago by John Wu <[email protected]>
[torch-mlir] update e2e test class documentation (#2722)

The doc seems copy-and-paste from the linalg-on-tensors class

3e9bacdb514af36dea80f4e40d251f2a2cca4c4e authored 12 months ago by Aart Bik <[email protected]>
add basic cumsum. this doesn't support the exclusive and reverse attrs (#2717)

fixes #2711

1778314620b796de7a7aba61f00396cecbd29a0b authored 12 months ago by Xida Ren (Cedar) <[email protected]>
build: manually update PyTorch version

Set PyTorch and TorchVision version to nightly release 2024-01-02.

Signed-Off By: Vivek Khandel...

690827fe52768eff2be5b168581824de57de2e1b authored 12 months ago by Vivek Khandelwal <[email protected]>
Added tensorResultTypeAtIndex to Patterns.h

Need this for LayerNorm

80bd093d56c5f7b36c6852fdff05afac0d7c3a00 authored 12 months ago by Andreas Falkenberg <[email protected]>
Add support for reflection_pad1d (#2706)

Adds a lowering to Linalg for reflection_pad1d. Based on ideas/code from draft PR
https://githu...

9adad9bc407d92860b99f74b02da3a07b315d6b0 authored 12 months ago by kumardeepakamd <[email protected]>
lower torch.aten.isinf to linalg (#2638)

Co-authored-by: Rob Suderman <[email protected]>

6660a26594dc82cd3dd6fc33c9269ff09ecd263a authored 12 months ago by Xida Ren (Cedar) <[email protected]>
support Onnx opset 1-13 ReduceMean where axes is supplied as an attr (#2703)

(instead of an input)

Addresses part of #2689. fixes #2702

9fc212ea9afe0f1e31b4e2ee03bc6db296e84190 authored 12 months ago by Xida Ren (Cedar) <[email protected]>
Implement lowering of torch.aten.exponential (#2680)

https://github.com/llvm/torch-mlir/issues/2646

Decompose aten.exponential() into: -exp(1-x)/l...

8e389ff2ffac781648721696c716f141048c38c9 authored 12 months ago by Sungsoon Cho <[email protected]>
Lower `onnx.split` to `torch.aten` (#2686)

d560698e3d610ecdc56667c713e2338c47bf4f44 authored 12 months ago by Xida Ren (Cedar) <[email protected]>
[onnx] Add torch-mlir-import-onnx native port as an optional tool/library. (#2694)

As noted in the plan when this work started, we need to produce an ORT
EP plugin for a downstre...

1b40b6384e8d7e716f42142f90c00c653c7d2635 authored 12 months ago by Stella Laurenzo <[email protected]>
lower onnx max op to torch aten maximum op (#2618)

lower onnx min op to torch aten minimum op

2d796b750250b204fd0ad0d29f844b81db95578c authored 12 months ago by aldesilv <[email protected]>
OnnxToTorch support for onnx.Mul op (#2699)

336cfb64b531a3d34cae74f007448749420d64ac authored 12 months ago by aldesilv <[email protected]>
Fix since-opset too high (#2701)

Addresses two of the ops from
https://github.com/llvm/torch-mlir/issues/2689

https://github....

6847fc1fc69d71d1d9b9485881f80ea12218564f authored 12 months ago by Xida Ren (Cedar) <[email protected]>
onnx to torch pow support (#2656)

abc6b0a25a8d6d42b440a32514c508302767469e authored 12 months ago by aldesilv <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for GlobalAveragePool op. (#2692)

This commit adds the OnnxToTorch support for GlobalAveragePool op.

Signed-Off By: vivekkhande...

4f252c88b486c73f1d7bf776168c2ace09c2a169 authored 12 months ago by Vivek Khandelwal <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for Reshape Op (#2698)

This commit adds the OnnxToTorch support for Reshape op.

ee75e8d1ae72b0b4868c6dae383709b83eb7e842 authored 12 months ago by saienduri <[email protected]>
[MLIR][ONNX] Fix onnx.conv lowering to handle bias tensor

Signed-Off By: Vivek Khandelwal <[email protected]>

0849fd0a0681598e1eaadf8bcc23699235819973 authored about 1 year ago by Vivek Khandelwal <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for BatchNormalization and Concat op.

This commit adds the OnnxToTorch support for BatchNormalization and Concat op.

Signed-Off By: v...

9a72c6584e72f009eae765956cfd8a9d55f49497 authored about 1 year ago by Vivek Khandelwal <[email protected]>
[onnx] Fix importer variable names to make `mlir` legal (#2690)

Some names for `onnx` identifiers are not legal in `mlir-ir`. Sanitize
so that the generated `i...

85b86b36a28ceebbe57d9aca4083708ea8e675af authored about 1 year ago by Rob Suderman <[email protected]>
[fx] Upstream the turbine FxImporter to torch-mlir. (#2681)

Changes made during upstreaming:

* Removed comments attributing some copied code back to torc...

ccd469ca0d626d29fea3ab35d5956cc2882a12be authored about 1 year ago by Stella Laurenzo <[email protected]>
[onnx] Lower onnx.HardSigmoid to torch (#2682)

The expression for HardSigmoid in Onnx
(https://onnx.ai/onnx/operators/onnx__HardSigmoid.html):...

46f2cb50dca5e789d1114b127d9a4312fbb8e3d9 authored about 1 year ago by John Wu <[email protected]>
Mentioned helpful tooling to convert Onnx models to Torch MLIR (#2683)

- Going through the `#torch-mlir` channel on the `llvm` discord, I
realize that there are some ...

779a141f8d6a276c73ddcf6fea5ee40ae39be0d2 authored about 1 year ago by John Wu <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for Conv and ConvTranspose op.

This commit adds the OnnxToTorch support for Conv and ConvTranspose op.

Signed-Off By: vivekkha...

3226241521f67c3b54a61f5cc6df265059da2c5f authored about 1 year ago by Vivek Khandelwal <[email protected]>
NFC: Remove unused variable causing a warning.

d75cff6cd1ce691083708ff0226ebb1dd02ef5ee authored about 1 year ago by Stella Laurenzo <[email protected]>
Allow printing all IR in `torch_mlir.compile` (#2669)

This PR adds the `enable_ir_printing` option to `torch_mlir.compile`,
which can be used to prin...

832899817210ce506e9be9888cb2f7d2a5b59630 authored about 1 year ago by Rik Huijzer <[email protected]>
[onnx] Lowerings from `onnx.tan` (#2642)

Started work on the `tan` lowerings for ONNX to Torch. Uses `sin` and
`cos` to represent a `tan`.

11cc92d4ab41d29a7478fc330b8fc9debf469481 authored about 1 year ago by Rob Suderman <[email protected]>
[aten] Make `torch.aten.matmul` to `linalg` work for non-broadcasting case (#2659)

Broadcasting for `torch.aten.matmul` is optional so a MxN with NxK
matmul should be legalized t...

a24aadbfab8eea598a982dd9f56178c2ba5561ab authored about 1 year ago by Rob Suderman <[email protected]>
Tweak development.md for more speed (#2667)

Adding the `--progress` flag shows the same output as what `git clone`
would show. This is very...

8fa81d181b3abf032f23245eadbfe9801d1ddbd3 authored about 1 year ago by Rik Huijzer <[email protected]>
Fix typo in DecomposeBernoulli() match failure messages. (#2676)

20ab88284098e6ef4250d652609dc89542aa1d54 authored about 1 year ago by Sungsoon Cho <[email protected]>
Integrate llvm/llvm-project@99045b60b575 to fix bazel build. (#2677)

https://github.com/llvm/torch-mlir/commit/be3e74b647375d1c72f075bebf77dc31e74477a2
breaks bazel...

869c25877a492ce214e87023e45919fd225ad145 authored about 1 year ago by Han-Chung Wang <[email protected]>
Integrate llvm/llvm-project@282d50147628 (2023-12-19) (#2675)

be3e74b647375d1c72f075bebf77dc31e74477a2 authored about 1 year ago by Han-Chung Wang <[email protected]>
[ONNX] ONNX -> TORCH for Erf (#2673)

TorchOnnxToTorch
For Erf function

ebaab4200f2c9dd7dc817361e916b69eb0379ff8 authored about 1 year ago by Andreas Falkenberg <[email protected]>
Update PYTHONPATH in development.md (#2644)

Modify PYTHONPATH to new related directory in docs.

89cfbe894df2592a296f48440005da244768b0fa authored about 1 year ago by Yinrun Lyu <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for AveragePool op. (#2672)

This commit adds the OnnxToTorch support for AveragePool op.

Signed-Off By: vivekkhandelwal14...

8649b84e3f768daec7d43dc439f1d91cb44a9c6e authored about 1 year ago by Vivek Khandelwal <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for Reduction Ops (#2657)

This commit adds the OnnxToTorch support for ReduceSum, ReduceMean, and
ReduceMin ops.

698ff3a736be3dcc201b4f5a7297f417587f3a99 authored about 1 year ago by saienduri <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for Gelu (#2647)

This commit adds the OnnxToTorch support for Gelu op.

---------

Co-authored-by: Rob Suderm...

deacb8ef38757386e4303d780c7a74fb06b87e39 authored about 1 year ago by John Wu <[email protected]>
[torch] Lower `torch.aten.sinh` to `linalg` (#2662)

791c66647927a35c610ecd2ca2d93401f761b422 authored about 1 year ago by Rob Suderman <[email protected]>
[Bazel] Add conversion targets for `TorchToTensor` (#2666)

Adapts bazel build per https://github.com/llvm/torch-mlir/pull/2648.

https://github.com/sj...

9c655d0bfb166785dc17e51b0afa1f937c227cef authored about 1 year ago by Sambhav Jain <[email protected]>
[onnx] Lower `onnx.Gemm` to `torch` (#2663)

General lowering for `onnx.Gemm` to `torch`

ae1a6e4a5a058170dd7b63001322844d04d12aac authored about 1 year ago by Rob Suderman <[email protected]>
[onnx] Support of onnx.Greater, onnx.Less, onnx.GreaterOrEqual to Torch (#2649)

The three remaining compare operations
onnx.Greater
onnx.Less
onnx.GreaterOrEqual

Are al...

cee8563060c79766ae530e539167bd8c872561db authored about 1 year ago by Andreas Falkenberg <[email protected]>
[onnx] Add support for `onnx.sinh` (#2643)

Adds a lowering from `onnx.sinh` to `aten.sinh`. This includes adding
the `aten.sinh` operator.

61888690bba0b766cd3e4fc16ce1d43b3b70b44f authored about 1 year ago by Rob Suderman <[email protected]>
Bump LLVM version to aa165edca8545b212de084d5b18c3d30347f774a (#2658)

b3e94208a891a85cffc5eec1b267ce4e7a761b74 authored about 1 year ago by Rob Suderman <[email protected]>
[onnx] Lowerings from `onnx.transpose` (#2641)

Lowerings for `transpose` from ONNX to `aten`. Implementation depends on
making multiple `aten....

705ea958ae1406e2f7cbff442c13db05587d3b33 authored about 1 year ago by Rob Suderman <[email protected]>
[TorchToLinalg] Lower aten.cat to tensor.concat (#2650)

This replaces the lowering of aten.cat with tensor.concat, allowing more
efficient handling of ...

030b0140d45559743dff85573ca00ba10cce7a5a authored about 1 year ago by Quinn Dawkins <[email protected]>
[onnx] Lowering for `onnx.shape` to `torch` and `tensor` (#2648)

Includes the lowering from the `aten` equivalent to `tensor` operations.

061af696ce94c932152bdf64ca7eba3b4034b367 authored about 1 year ago by Rob Suderman <[email protected]>
Implement lowering of aten.cosh op. (#2635)

55e9401c5ca13aaa4a327bf5ed91583a9e5a9f4d authored about 1 year ago by Sungsoon Cho <[email protected]>
[ONNX][MLIR] Add support for LeakyRelu and GatherElements op (#2655)

This commit adds support for `LeakyRelu and GatherElements` op in the
onnx pipeline.

Signed-...

eb9249e601b0a3b01650f07b8c99b2b8a3a3a190 authored about 1 year ago by Gaurav Shukla <[email protected]>
Bump LLVM version to fcd54b368e6713acd236dc47401b5292755900d7 (#2654)

This bumps the llvm submodule to HEAD to pick up recent fixes.

d9f4a80b10ae849a0615674e87751b78d00be241 authored about 1 year ago by Quinn Dawkins <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for q-z ops (specific ops in description) (#2601)

This commit adds the OnnxToTorch support for Reciprocal, Round,
ScatterElements, Sigmoid, Sin, ...

f59c01fd2fbcb5162b8147f34c68cd970f2c26a9 authored about 1 year ago by saienduri <[email protected]>
[onnx] add support for onnx.LessOrEqual (#2639)

Added the less or equal operation to OnnxToTorch.
onnx.LessOrEqual

---------

Co-authored...

4ec8b9fc02adfab64f363ee40e6949ea73b9a628 authored about 1 year ago by Andreas Falkenberg <[email protected]>
Bump LLVM version to 762964e97fd66ab7728ecc92aa153a61266fa9df. (#2645)

65f517b3d0956bcebeeb362c0b841216e18d314b authored about 1 year ago by Sungsoon Cho <[email protected]>
[onnx] Lowerings from `onnx.selu` (#2634)

Lowerings for `selu` lowerings for ONNX to the corresponding torch
implementations. Torch's `se...

4857606ffe3a04f6f040ca3f829904d292afba2e authored about 1 year ago by Rob Suderman <[email protected]>
[torch] Add support for aten.selu (#2640)

Add `aten.selu` operation to `torch` dialect.

6ddeb1a6efe7f61e80be3791952dc7c730dc1c72 authored about 1 year ago by JianzheXiao <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for matmul ops (#2629)

This commit adds the OnnxToTorch support for Matmul.

42392bc84524cff83f6e87e17b02e563aebf2122 authored about 1 year ago by John Wu <[email protected]>
[onnx] Add torch-mlir-import-onnx tool. (#2637)

Simple Python console script to import an ONNX protobuf to the torch
dialect for additional pro...

ed4df38e8d86083c4dcc1b58f7d59a4c8cf6ab85 authored about 1 year ago by Stella Laurenzo <[email protected]>
[Torch Dialect]Add Support for AtenGroupNormOp and AtenNativeGroupNormOp (#2591)

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

7cf52ae73f59ae90abcdbe3e7f60bef95e1a59eb authored about 1 year ago by JianzheXiao <[email protected]>
Upstream the ONNX importer. (#2636)

This is part 1 of 2, which will also include upstreaming the FX
importer. I started with ONNX b...

74f7a0c9d6ea5b3a6d37dd61d0a83557a90b1d03 authored about 1 year ago by Stella Laurenzo <[email protected]>
Sort the TOSA passing test list (#2630)

For easier tracking of issues, sort the TOSA passing list. It is still
significantly smaller th...

f67249d34fe9edaa98c1229a3eccd0522f55aea4 authored about 1 year ago by Eric Kunze <[email protected]>
Bump LLVM version to f7250179e22ce4aab96166493b27223fa28c2181

099e1f4cf5cc070d411f404e08d1e25eaa648efe authored about 1 year ago by Frederik Harwath <[email protected]>
Implement e2e support for aten.acos op

This depends on a change in the LLVM core repository which adds acos
support to the MLIR Math di...

b656c674eec283ffe6f4090734d6d62ab2c8f5ac authored about 1 year ago by Frederik Harwath <[email protected]>
Remove folder from `AtenStackOp` for single element list inputs (#2626)

`AtenStackOp` defines this folder for list operand containing single
element:
```
OpFoldResul...

7acabafd840ce6c11ba64c7105cda53db1b1c4f6 authored about 1 year ago by Sambhav Jain <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for bitwise and math ops

This commit adds the OnnxToTorch support for BitwiseXor, BitwiseOr, Div, Equal, Cast,
Ceil, Floo...

0b4422a2532a1ed673de33c17c86f038e9354969 authored about 1 year ago by Vivek Khandelwal <[email protected]>
[Torch Dialect] Support Einsum Op (#2230)

As title, support torch.aten.einsum op

Right now only support Static Shape, because of the kn...

96fcde4d77d8f77ecb0fe58061a671f258870924 authored about 1 year ago by JianzheXiao <[email protected]>
[MLIR][TORCH] Add support for Short(si16) data type

Signed-Off By: Vivek Khandelwal <[email protected]>

07c3e11f5648361320ba7018daee8b2d873ee956 authored about 1 year ago by Vivek Khandelwal <[email protected]>
[TorchToLinalg] Lower grouped conv2d to linalg Op with correct dimension ordering (#2623)

The linalg Op `linalg.conv_2d_ngchw_fgchw` had a bug where

1. Weights were accessed as G,F,C,...

fb21a858748d6c1945aa6a284d75f376458d9242 authored about 1 year ago by Felix Schneider <[email protected]>
Advance llvm-project and stablehlo. (#2619)

llvm-project: bbd2b08b95fe76bea138c1b03c1cd42ed3ee04df
stablehlo: ab709fe48de88c67717abfbd7ef17...

8252656b6dadb9781eaf7d025380ca9d664f45e0 authored about 1 year ago by Stella Laurenzo <[email protected]>
[TorchToLinalg] Drop constexpr from ifs in argmin/max.dim (#2617)

MSVC-19 does not support constexprs of lambda captured constexpr values
like this: https://godb...

63505ad6b2d840c409bb92df460caed5cecf6447 authored about 1 year ago by Quinn Dawkins <[email protected]>
[TorchToLinalg] Fix integer type handling for aten.mm (#2615)

Despite aten.mm requiring the input and output types match, we still opt
to maintain signedness...

141202bc0140c0797d9c15959c7fa5b74abe4ba4 authored about 1 year ago by Quinn Dawkins <[email protected]>
Add a decomposition for torch.aten.argmin (#2613)

Adds a lowering for the torch.aten.argmin operator to linalg via decomposition into torch.aten.m...

c0115706a072173928d80199f2a8ebc5ffcb978f authored about 1 year ago by frafranz <[email protected]>
Regenerate GeneratedTorchOps.td after recent change to torch_ods_gen.py (#2612)

Try to fix the error reported by @qingyunqu in #2609.

6244f301fb063be15dc5df27f77567fb8852e31f authored about 1 year ago by Frederik Harwath <[email protected]>
Add aten.min.dim to linalg lowering (#2600)

6248216dca711100c0c6d770e6a7a3e9fc81bcb0 authored about 1 year ago by Frederik Harwath <[email protected]>
Recommend update_torch_ods.sh for re-generating GeneratedTorchOps.td (#2609)

Fix #2608

d0b49a912ea3f066cee600f4385b5f08dacccd8e authored about 1 year ago by Frederik Harwath <[email protected]>
build: manually update PyTorch version

Set PyTorch and TorchVision version to nightly release 2023-12-04.

Signed-Off By: Vivek Khandelw...

10b5432e7d29933fc049cbea7b4dfc2b83009176 authored about 1 year ago by Vivek Khandelwal <[email protected]>
[TorchToLinalg] NFC: Move Utils.h to an externally accessible location (#2603)

400752ca8d388a58ab6b9bc0ea6f8b6107786590 authored about 1 year ago by Quinn Dawkins <[email protected]>
Update out of date docs (#2602)

Some of docs referred to old file paths that no longer exists. This
patch updates some of the i...

7d0f5cc5a80bede3c61911e5b77016a48880f5f8 authored about 1 year ago by srcarroll <[email protected]>
Move handling of integer signedness to the backend conversions (#2597)

The function `getTypeForScalarType` currently takes an argument to
specify the signedness of in...

e568f7e99980722f22e988cd2fe1b437be614ce5 authored about 1 year ago by Ramiro Leal-Cavazos <[email protected]>
Bump LLVM and StableHLO (#2598)

Bump LLVM to `5e5a22caf88ac1ccfa8dc5720295fdeba0ad9372` and StableHLO to
`83f095e7217c897f1ecca...

44f6942796536a7cf2eee37ec383c9db74fa853f authored about 1 year ago by Sambhav Jain <[email protected]>
[Torch Dialect] Decompose AtenTriuOp (#2561)

decompose like:
```
import torch

def my_triu(x, diag):
rows = torch.ops.aten.size(x, -...

f7a92d346ee8f498eb35d764d81cfd00bcdbf119 authored about 1 year ago by Mi Jiazhi <[email protected]>
Add bazel targets for TorchOnnxToTorch conversion passes (#2596)

Adapts to the TorchOnnxToTorch changes from
https://github.com/llvm/torch-mlir/pull/2585.
Also...

49fdc1a8a6957431a34b2bb62774ba10de3a9895 authored about 1 year ago by Sambhav Jain <[email protected]>
[MLIR][ONNX] Add OnnxToTorch support for atan and bitwise ops

This commit adds the OnnxToTorch support for Atan, Bitshift, BitwiseAnd,
and BitwiseNot op.
This...

dc9ea08db5ac295b4b3f91fc776fef6a702900b9 authored about 1 year ago by Vivek Khandelwal <[email protected]>
Run CI on all main/postsubmit commits.

Prior to this, the concurrency rules for presubmits (which cancel eagerly) were being applied to...

53fc995639e26f40465516dded26548928bd2d1a authored about 1 year ago by Stella Laurenzo <[email protected]>
Temporarily disable bazel build until fixed.

2148c4cd0d95d16ce11d44be7a545bdf2bda9889 authored about 1 year ago by Stella Laurenzo <[email protected]>
Move TORCH_MLIR_USE_INSTALLED_PYTORCH to top-level.

This was unfortunately being initialized in a directory below its first use. This was causing th...

66b73edb286fb5c0f1ace2b0b4b147bf9edbc3e7 authored about 1 year ago by Stella Laurenzo <[email protected]>
Improve decomposition of pixel_shuffle (support dynamic shapes) (#2590)

The aten.reshape ops in the decomposition are replaced with prims.collapse
and prims.split_dim...

1b7d6f2af91429c5a8e680faafaadd1b843cb0ca authored about 1 year ago by James Newling <[email protected]>
Initial TorchOnnxToTorch conversion pipeline. (#2585)

Adds a pipeline to convert custom ops and metadata represented as
`torch.operator` custom ops t...

e06efc51363227f425ef40e8b5bf0f76e0cfb592 authored about 1 year ago by Stella Laurenzo <[email protected]>