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
Where operation can be statically computed when involving splats of
known value. Added handling...
Folds aten::index_select ops under the following conditions:
1. If the input and output are t...
23647ab2d178f8f2edc3bb4a0c207cca7d347ca5 authored 11 months ago by Dave Liddell <[email protected]>Lowering of torch.aten.all.dim to linalg.
Per PyTorch documentation:
> This function match...
32dbf99ce24cd8ebf17db0dcba97a46f5f7a70d4 authored 11 months ago by mmakevic <[email protected]>Includes `slice` folder and lit tests
---------
Co-authored-by: Xida Ren <xida.ren.dev@gma...
fc04bc7ee9732428baf6fdba2a728b2b3bee021a authored 11 months ago by Xida Ren (Cedar) <[email protected]>Just a one line change in a .md file
723b8b1d285638b8b0e594345df821a6f1f8c468 authored 11 months ago by James Newling <[email protected]>
Link to related RFC:
https://discourse.llvm.org/t/rfc-rename-torch-mlir-compile-apis-and-introd...
A chunk off
https://github.com/llvm/torch-mlir/pull/2856
https://github.com/llvm/torch-mlir/...
Adds an escape hatch from creating a DenseResourceElementsAttr for
single value tensors into De...
If a tensor is initialized by a list with a single constant integer,
this folder turns it into ...
Simple missing scalar operation for multiply floats was missing.
041a54ae0c29e04703f0d9616bc4effebf2e6998 authored 11 months ago by Rob Suderman <[email protected]>
Leaning on the QDQ functionality in torch we can support the QLinearConv
operation by piggyback...
The existing `flatten` lowering did not define what the intermediate
shape was. This could resu...
b3a56c0711fcd49698ebaa73173fc7fcd986cf34 authored 11 months ago by Xida Ren (Cedar) <[email protected]>
Signed-off-by: Gaurav Shukla <[email protected]>
f4562a8eaa3d13e17768f50164ede38383f7983e authored 11 months ago by Gaurav Shukla <[email protected]>d1cd117998d5d9b6d0f68784119d38a6b191463a authored 11 months ago by Aart Bik <[email protected]>
So that the CumSum Op in OPT can get the constant that it requires to be lowered to TMTensor
...
24b8c8672ae4366025aa8cb3155dedb58c8e3450 authored 11 months ago by Xida Ren (Cedar) <[email protected]>
`[build]
D:\Dev\iree\third_party\torch-mlir\lib\Conversion\TorchOnnxToTorch\DefaultDomainGtoP.c...
`torch` requires that padding be symmetric for pooling operations. To
support non-symmetric pad...
Fixes bazel build error:
```
ERROR: /root/.cache/bazel/_bazel_root/b89349c08f7224396763d14fe35...
Fix for https://github.com/llvm/torch-mlir/issues/2765
The onnx docs say that you can't do sh...
04be6ba77308a836779c237be984077a09f6683d authored 11 months ago by Dave Liddell <[email protected]>
We do not support average pool when `countIncludePad is set to false.
However if the input is u...
Extracting scalar values from tensors can be implemented via a lowering
to tensor.extract.
With the recent LLVM integrate and changes from
https://github.com/llvm/llvm-project/pull/78260...
To handle the conversion from raw bytes to `DenseElementsAttr` we need
to handle the endianness...
`onnx` explicitly specifies that `raw_data` is stored in `little-endian`
layout. While converti...
Closes nod-ai/SHARK-Turbine#356
54ef18c556c10402027eca04b27b0384a2647da1 authored 11 months ago by Ilija Kalinić <[email protected]>
Required some massaging of LTC to make it warning clean, and I had to
manually disable some war...
943164d797f2f20a4c9a3d792f824b3ecd5ecc70 authored 11 months ago by Stella Laurenzo <[email protected]>
26c0ecd09c532204b80e2145bcbe1539238e4c33 authored 11 months ago by Stella Laurenzo <[email protected]>
Note that we are waiting for actual FX traced graph support for sparse
tensors. For details see...
This PR adds a check to the CI right after checking out the Torch-MLIR
repository to make sure ...
d778950f455ff479875de78f6b421a3e9adfd7a9 authored 11 months ago by Yuanqiang Liu <[email protected]>
Linalg has quantized specific operations. We can lower to these
operations when there is a know...
We were seeing some assertion failures after some checks around folders
were tightened up in LL...
db67bc555ade76a26ea96d733050508e0a60822b authored 11 months ago by Rob Suderman <[email protected]>
Change should be visible :
https://github.com/newling/torch-mlir/blob/docs_update/docs/developm...
See change in test for what the new message looks like.
1e882f58035171ae2c9d2d1533fbf32569be7d12 authored 11 months ago by James Newling <[email protected]>Signed-Off By: Vivek Khandelwal <[email protected]>
e18fcebd3af1659ab3eeaa9db75534cf0fe03eaf authored 11 months ago by Vivek Khandelwal <[email protected]>Fixes https://github.com/nod-ai/SHARK-Turbine/issues/352
eff325abc3e7bba294e50d3c5c320a61bd62fab6 authored 11 months ago by aldesilv <[email protected]>
This allows the following command to be used to ignore sweeping
formatting changes.
```
git...
After noticing a number of commits with unrelated formatting changes,
I think something was cha...
Torch does not have an equivalent matmul operation for integers. Instead
it sidechannels the in...
TypeRange is an ArrayRef<Type> and therefore cannot be safely
instantiated from a list initiali...
032f225fa513b8eb781a11a0e27cb759943594cf authored 11 months ago by Stella Laurenzo <[email protected]>
6b3ebb237fbf9103f63a66fc41c2e27e15ab0c8c authored 11 months ago by Stella Laurenzo <[email protected]>
4513c3ca8702fd4fac96673207559556bb21d114 authored 11 months ago by Stella Laurenzo <[email protected]>
Per the RFC and numerous conversations on Discord, this rebuilds the
torch-mlir CI and disconti...
4a4d80a6ad18b01b7eaf096c5231106228fd719c authored 11 months ago by Stella Laurenzo <[email protected]>
28c7051ceb5a49944dfbd0d1fdf1ada4ac2a5b9e authored 11 months ago by MaheshRavishankar <[email protected]>
This preserves sparsity at the most obvious places of lowering TORCH
tensors to MLIR RankedTens...
Signed-Off By: Vivek Khandelwal <[email protected]>
da7c6d2c16439ff5a009bd660567d38158fc3049 authored 11 months ago by Vivek Khandelwal <[email protected]>4964977e8571e7f14c25581188f7cba4cf6904ca authored 11 months ago by Phaneesh Barwaria <[email protected]>
As that torch with py3.9 is also used widely.
e73c5368fb26ea80ad4ba495f699b92cb4f2bc73 authored 11 months ago by Yuanqiang Liu <[email protected]>
Support a lowering for dequantization for per channel tensors from
`torch` dialect to a linalg ...
0aed231e216ea8cd84aa64887d94a57a2c2c5f36 authored 11 months ago by Aart Bik <[email protected]>
fe836ceebf48e369bc6f2904c64704559dbb9689 authored 11 months ago by Aart Bik <[email protected]>
dc9c624a29d8b5ca42f0e5d6474837cf12ea410c authored 11 months ago by Aart Bik <[email protected]>
This adds an encoding field to the torch type, using the interfaces for
printing, parsing, and ...
Code used for testing.For the location of CumsumInputDtypeInt32Module in
the repo you can see
...
This includes custom op matching for decomposed operations and fusing
dequantization into dense...
We can plumb the linear matmul into pytorch using its quantized types
with side channel informa...
Signed-Off By: Vivek Khandelwal <[email protected]>
894805dd5e21c3255a6352606a76145740085b92 authored 11 months ago by Vivek Khandelwal <[email protected]>
This commit adds mapping from `onnx.pad` op to `torch.pad` op. Currently
it does not support `a...
ac8975ea1276e1f53f1bb3eaedc26f32252c91a1 authored 11 months ago by Phaneesh Barwaria <[email protected]>
The logic here is very similar to the conversion for AdaptiveAvgPool1d
#2661 with a few modific...
Signed-Off By: Vivek Khandelwal <[email protected]>
311b6b0286bfa016346bc7fd8b441bbd50216060 authored 11 months ago by Vivek Khandelwal <[email protected]>
convolution with [time,batch,channel] ordering, as opposed to the
default [batch, channel, time...
https://github.com/nod-ai/SHARK-Turbine/issues/312
77ae56337dbf95eb809f4a7d218a9fb3dc1f41b0 authored 11 months ago by Chi_Liu <[email protected]>dc056e58e6e6b19a1b686ab7c04c12274864ffd7 authored 11 months ago by James Newling <[email protected]>
Set PyTorch and TorchVision version to nightly release 2024-01-22.
Signed-Off By: Vivek Khand...
c9d8ffb414df5451ee7f193af501afbd9c03a102 authored 11 months ago by Vivek Khandelwal <[email protected]>Signed-off-by: Gaurav Shukla <[email protected]>
b7a032967678491bb4765a10b73e8a99c1c76b60 authored 11 months ago by Gaurav Shukla <[email protected]>Fixes https://github.com/llvm/torch-mlir/issues/2764
In the case of OPT, there are ConstantO...
d452c4f4c0d5b8fe748eebb1b9801f44a7d13374 authored 11 months ago by Dave Liddell <[email protected]>https://github.com/nod-ai/SHARK-Turbine/issues/331
cad98e81136c289694661baadd57759e817eaff7 authored 11 months ago by Chi_Liu <[email protected]>5883ef0f21b526e399f1f6bd6fd8f548ef3a7115 authored 11 months ago by Ramiro Leal-Cavazos <[email protected]>
Currently transposed convolution is not handled correctly by
`TorchToTosa`. This PR allows tran...
b9806cfa3823bb68faef39fbbb284eda92c0e906 authored 11 months ago by Franz Haniel <[email protected]>
Introduced in 704cfdaf0893fa4078ab744a915a56367282dcaa of @wu-s-john
g++ compiler error:
...
50ac3b1912516b064a94d2414be295be79b09bc5 authored 11 months ago by James Newling <[email protected]>[https://github.com/nod-ai/SHARK-Turbine/issues/328](url)
---------
Co-authored-by: Dave L...
2f4924015de915f7cd8f12500af2018fe3977fbe authored 11 months ago by Dave Liddell <[email protected]>
Overly specific docs can get stale easily. It looks like
https://llvm.github.io/torch-mlir/pack...
18669b38cbc42af1eff625af86a5f7faa356d76a authored 11 months ago by Xida Ren (Cedar) <[email protected]>
This commit adds support for gather op in the onnx pipeline.
https://github.com/nod-ai/SHARK-Tu...
Added verification logic to the abstract_interpreter_lib_gen.py
Also made some unit tests
...
704cfdaf0893fa4078ab744a915a56367282dcaa authored 11 months ago by John Wu <[email protected]>Closes nod-ai/SHARK-Turbine#349
faa4517e83d82348259165412d0744ba776360b3 authored 11 months ago by Ilija Kalinić <[email protected]>4de4d38b870598f766fd78653028d5bd4b27fff2 authored 11 months ago by Andreas Falkenberg <[email protected]>
We can make the per-tensor version of the operation to the dequantize
operation via marking wit...
We can map the per_tensor case to the `torch.aten.quantize_per_linear`
operation. In this case ...
This PR add torch-to-tosa lowering support for AtenLinalgVectorNormOp
e2e test:
python -m e2...
eed144bfbc4cf9eafebba1949aa81f615a865eea authored 11 months ago by Phaneesh Barwaria <[email protected]>
a8538e1e3fb98c5d2c6170dd0e5d549d1d6b2632 authored 11 months ago by Sungsoon Cho <[email protected]>
f85e5c932bb6462d66d290ac11860e916f77243a authored 11 months ago by lonely eagle <[email protected]>
prims.expand expects the start and end dimensions to be strictly less
than the rank of the tensor.
Implemented ONNX.Range. The spec says the data type for start, limit,
delta are 0-D can be doub...
Co-authored-by: Lisa Liu <[email protected]>
09421b1cf3153e9794187fe665395713a048803f authored 11 months ago by lisaliu1 <[email protected]>
Handles the multiple cases of `onnx` constant values and converts them
to `torch` literal tenso...
- Add fixes for
https://github.com/llvm/llvm-project/commit/af78e5daf0791135485dbd7972ffedb9277...
Handle both `torch.dequantize` and `torch.quantize_per_tensor` including
the op based quantizat...
Add Maxpool ONNX op support.
Add Utils.h/cpp files to create a constant int list for ONNX.
This PR updates the torch-to-tosa conversion with following changes:
- Support torch.none as ...
670a99ae196da892310776f110cfe29dfb68a174 authored 12 months ago by Ze Zhang <[email protected]>47ffc90db49f16c126c1fa456b92e24161847afb authored 12 months ago by James Newling <[email protected]>
Closes nod-ai/SHARK-Turbine#290
e1a86e480a5687f78ad4b70047e978905bee5088 authored 12 months ago by Ilija Kalinić <[email protected]>