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
See https://github.com/llvm/torch-mlir/issues/647#issuecomment-1114328241
f31743b6518df46437abdc55eba7d7e855d9430f authored over 2 years ago by Sean Silva <[email protected]>This commit adds lowering of `aten.avg_pool2d` op.
Signed-Off By: Vivek Khandelwal <vivek@nod-l...
4b1128444007a3d9e07eeb01bb697e58663a1e7a authored over 2 years ago by Vivek Khandelwal <[email protected]>
This commit fixes the `ConstantPad2dStaticModule` test case by adding
the lowering of `aten.pad`...
This patch updates the `torch_mlir::convertTensorToMlirElementsAttr()`
method to enable the cre...
BART, BigBird and GPT2 are not being serialized and hence removed.
Also, changed the script to o...
1. This commit adds lowering of "while-like" prim loop to scf.while
operation.
2. Adds lowering ...
Uses the latest snapshot tags and adds the releases to same asset
directories so it can be run ...
Fix the inplace update tensor issue we had
where the torchscript execution would update the inpu...
This reverts commit 78f5747568f4ae9e95a83f680dc066a185ddff92.
5ef9f501fae5d97a614e01381efb84e4616687ee authored over 2 years ago by Sean Silva <[email protected]>This reverts commit 51dd4625927329f528b549faec90ff0be2d93392.
7669ee4e4af23ff96a47a8f88b216f2318df7f0f authored over 2 years ago by Sean Silva <[email protected]>This reverts commit 1f102cc400a72fa0926eb79f657e347af7c2d142.
eff144c0b797440905028e3247d749f396d2bf36 authored over 2 years ago by Sean Silva <[email protected]>This reverts commit 564734b2d7573e66b6b26ac81d35e0df01952102.
44c7b181d34dcb1d832fa0d742791fd7fee4be64 authored over 2 years ago by Sean Silva <[email protected]>
This commit decomposes `aten.index_put.hacked_twin` op into
`valsem.aten.index_put_impl` op.
Si...
e57e1968bc17cc98cbaef6c8355f9fce0dfd249e authored over 2 years ago by Vivek Khandelwal <[email protected]>
This commit adds more test cases `aten::index_put` op.
This commit also fixes formatting issues ...
57a28dfadce3c4f212355c3705df0b404514f660 authored over 2 years ago by Ahmed S. Taei <[email protected]>
This commit adds lowering of `aten.ceil.float` op.
This commit also fixes formatting for the fil...
86eb493a443ffceada475e33dcd648628b16a808 authored over 2 years ago by Yi Zhang <[email protected]>
Compiling torch-mlir against a source version of PyTorch or an official
wheel compiled with the...
This commit adds lowering of `aten.ne.float_int` op.
Signed-Off By: Vivek Khandelwal <vivek@nod...
51dd4625927329f528b549faec90ff0be2d93392 authored over 2 years ago by Vivek Khandelwal <[email protected]>This commit adds lowering of `aten.ge.float` op.
Signed-Off By: Vivek Khandelwal <vivek@nod-lab...
564734b2d7573e66b6b26ac81d35e0df01952102 authored over 2 years ago by Vivek Khandelwal <[email protected]>This commit adds lowering of `aten.div.float` op.
Signed-Off By: Vivek Khandelwal <vivek@nod-la...
f5b6c4b601d5dce93162b8e7ab654f9a45346c7a authored over 2 years ago by Vivek Khandelwal <[email protected]>This commit adds lowering of `aten.ge.float_int` op.
Signed-Off By: Vivek Khandelwal <vivek@nod...
1f102cc400a72fa0926eb79f657e347af7c2d142 authored over 2 years ago by Vivek Khandelwal <[email protected]>
I wasn't able to find exactly what frontend situation created it, but
`torch.jit.trace` will som...
7f2577a84832fabdd14bd45392af4f1af54b065d authored over 2 years ago by Ahmed S. Taei <[email protected]>
The updated LLVM code includes a patch to create bfloat16 array
attributes, thus enabling a dif...
Prior to this patch, the result type for several tensor operations could
only be float32, float...
* Update README.md
* Create development.md
Add a separate development.md file
a9ef4bb378e1730d902cb16e4f1cdc33bc514716 authored over 2 years ago by powderluv <[email protected]>50297864dfcd4c34b5bb13ea7434641ac78f317a authored over 2 years ago by powderluv <[email protected]>
This commit adds e2e heavydep tests for the torch benchmarks.
Signed-Off By: Vivek Khandelwal <...
4635d36efbb35fc1b3ed635631676a6351dc30f5 authored over 2 years ago by Vivek Khandelwal <[email protected]>Fix filename changed missed in Code Review.
2877a37ac6e436f5561f712c32b4d556bdd10647 authored over 2 years ago by powderluv <[email protected]>
env vars seems to be lost in manylinux docker.
Use a version file like IREE does.
* Add to eager tests to xfail while they are fixed.
Also XFAIL ConstantPad2dStaticModule_basi...
693f79a2b63e72d3b2af5f6528b0fe37ec6c394a authored over 2 years ago by Maksim Levental <[email protected]>- Add bazel GitHub actions.
6b3d0b7e7aecfb679d7d5387af272452f46ac52a authored over 2 years ago by Ahmed S. Taei <[email protected]>Set the environment variable and export it since it doesn't seem to get passed down.
7d9138f4978a0cebdc0c7de6c7cd8ba966e99931 authored over 2 years ago by powderluv <[email protected]>0f751498a7dddbf1759fdef7056c42eb94effb86 authored over 2 years ago by powderluv <[email protected]>
only upload torch*.whl to unblock OSX build failures during upload. We have to move to svenstaro...
d789aee11e3f765c06246aca38fdf8511c3d7b70 authored over 2 years ago by powderluv <[email protected]>
Example to demonstrate the extraction of forward as well as
backward graph via Functorch's AOT m...
Prior to this patch, the top-level README did not include the line for
running the Python regres...
Update artifact directory to ./build_tools/python_deploy/wheelhouse/*.whl
cbf158f069a719bb6d9ed4eea2b0cf0cb9583112 authored over 2 years ago by powderluv <[email protected]>Comparing index type instead of integer types solves the problem.
5cdef0213dc62edb37bf7997ea59a5449bb1c032 authored over 2 years ago by Prashant Kumar <[email protected]>remove now deprecated inputs to build and test
9f2184da9845b101002ce79d4f0015a858d0a9df authored over 2 years ago by powderluv <[email protected]>8003b92fa774b0f937e3eb00583adf70d6d49c0c authored over 2 years ago by powderluv <[email protected]>
c1026fa95b133d5032df66dfbdb68ae73a985724 authored over 2 years ago by powderluv <[email protected]>
Sets up auto-pinning of latest torch-nightly
4ef61aa27f1cec6146d317519e844aceace8bf14 authored over 2 years ago by powderluv <[email protected]>use sudo for mac OS
0257d91a21e51c45692de0d86ac45589d7dafeaa authored over 2 years ago by powderluv <[email protected]>fix build naming
299c1bbe6dbabf3b8a4af2a6407617f2cf131108 authored over 2 years ago by powderluv <[email protected]>
Update pinned pytorch version. Will submit a follow on PR to bump.
Also update artifacts directory
* Add oneshot release snapshot for test/ondemand
Add some build scripts to test new release f...
cc3a4a58ef7f8390d30b08c6d1b5b6f99a70b85e authored over 2 years ago by powderluv <[email protected]>
Added the dynamic registration of return function to the execution
engine. This makes sure that ...
This avoids issues where PyTorch version drift has made things
incompatible.
One caveat is that...
b69db60f858e250c0fe4c40a9bd157cdc8d6f20a authored over 2 years ago by Sean Silva <[email protected]>712b78c674c0962dddcdbedeef9325f14bc594cb authored over 2 years ago by Sean Silva <[email protected]>
This makes it much easier to convert models and hides all the
ClassAnnotator complexity.
This a...
075464fa741a8bcccfba1d303b8e52e4225d8621 authored over 2 years ago by Sean Silva <[email protected]>8d700dee2179c8802a44e8d25080cd569008a0ba authored over 2 years ago by Clément Fournier <[email protected]>
3e0c1cf6af00fafbd7d8e78de848ee31f26a5290 authored over 2 years ago by Clément Fournier <[email protected]>
578d0ec292e629c967553fa454383defc5642e65 authored over 2 years ago by Clément Fournier <[email protected]>
Since they run in distinct jobs, using the same ccache would
cause one job to overwrite the cach...
37087ccd5fd908cf6879378ef3f1f030bc0a89c9 authored over 2 years ago by Clément Fournier <[email protected]>
4a2535a86d027d5664729381e01b29b2f313931c authored over 2 years ago by Clément Fournier <[email protected]>
f9d5201ae62fa1010bfbca0315bd24fddf81e6ad authored over 2 years ago by Clément Fournier <[email protected]>
2a0c56741834f5bb433d6d7c90494dd10b96bd0b authored over 2 years ago by Clément Fournier <[email protected]>
That way, downstreams don't have to duplicate this list.
Also, remove "external config" feature...
3b5310d6d27283e7f7f26b9e2aaa656581747044 authored over 2 years ago by Sean Silva <[email protected]>This commit adds lowering of `max_pool2d_with_indices` op.
Signed-Off By: Vivek Khandelwal <viv...
769f3a8870308c9d84d6de29adaefea8af19c249 authored over 2 years ago by Vivek Khandelwal <[email protected]>d3c08376affe5343d4ffd344023186f5c6877637 authored over 2 years ago by Ashay Rane <[email protected]>
* shape: add shape transfer function for aten.neg
Prior to this patch, the list of shape tran...
a893c7d5cffc35e376767d959063fe4c1553909d authored over 2 years ago by Ashay Rane <[email protected]>This commit adds lowering of `aten::max_pool2d_with_indices_backward` op.
This commit also fixe...
1bccb4fc8aa221cfb1146bcf778b75a95c52b39f authored over 2 years ago by Vivek Khandelwal <[email protected]>Builds whl package for OSX. Need to validate smoke tests next
91d3e7ba15847aaf014b4cefecc7ee279f26c878 authored over 2 years ago by powderluv <[email protected]>24f9de7120bcd95de3d341f325a46d19a6a2dc4c authored over 2 years ago by Maksim Levental <[email protected]>
d46f169c1a8443caa62b23b331779399f0d0c563 authored over 2 years ago by Maksim Levental <[email protected]>
66de821eafaf8a01f4f95c4ba15751330384f833 authored over 2 years ago by Maksim Levental <[email protected]>
NB: `shouldnt_normalize2` and `shouldnt_normalize3` currently XPASS i.e., args *will* successful...
18ef40acaf39b1f32dd1e292ce3883a1dad76ed1 authored over 2 years ago by Maksim Levental <[email protected]>9ec0683e928bdd1acea9aeb025ed542332fab902 authored over 2 years ago by gpetters94 <[email protected]>
fa0b24a73ce4e403b077c8d894fe7a12d97303bb authored over 2 years ago by gpetters94 <[email protected]>
RefineTypes doesn't handle shape refinement anymore.
e7721fb784cab320bcde21446a8738652d0168fe authored over 2 years ago by Sean Silva <[email protected]>torch.layout information has been added.
1d5b5a89e8e9ac75e4837b158fc4230eb7388b28 authored over 2 years ago by Prashant Kumar <[email protected]>This PR adds rules for building the compiler part with bazel, a followup PRs will build the pyth...
eaf34fa02bd2d90d89e2bee2313c161f417c0709 authored over 2 years ago by Ahmed S. Taei <[email protected]>
The lowering of `aten.ne.Scalar` op has been added to
the linalg backend.
This commit adds the following support to the op `nll_loss_backward`:
- `input` tensor can be r...
Follows up on #623 for out-of-tree builds of torch-mlir, which
added building `torch-mir-dialec...
e1c7c1f9c5f626a63ddf7bb07c50f6997fbdc16c authored over 2 years ago by Sean Silva <[email protected]>
14cf87633c06348363811dd8f3dbeeaea2165228 authored over 2 years ago by Sean Silva <[email protected]>
This commit adds support for multi-dimensional tensors as input to the
`_index_put_impl_` op. T...
Signed-off-by: Anup Gangwar <[email protected]>
Co-authored-by: Anup Gangwar <anup.gangwar...
ccf924d3df2061c707f1a758e5f8c5682d15aa5d authored over 2 years ago by Anup Gangwar <[email protected]>
The issue was in the canonicalizer for torch.aten.ge.int -- in cases
where the operands were swa...
This should make the releases sort properly when `pip`'s
`-f`/`--find-links` argument is used.
This commit decomposes different variants of `aten.where.*` op into
`aten.where.Self` op. It cov...
This commit decomposes `aten.new_empty` op into `aten.empty.memory_format` op.
This commit also...
2597c481f6a0719e1e3ee9d490c02c60607ef6af authored over 2 years ago by Vivek Khandelwal <[email protected]>
A recent PyTorch commit made ConstantPad2d call a helper function with a
`Union[int, float]` typ...
As per the docs on:
https://github.com/eregon/publish-release
> Note that the release must *not...
4f61b1fce104df7288eaf75e121628371a17a251 authored over 2 years ago by Sean Silva <[email protected]>I am investigating the breakage.
Also, fix "externals" rename in setup.py and some cases where ...
3a96078571b97fba380aa2f13a6a44332494b105 authored over 2 years ago by Sean Silva <[email protected]>
The reified code to compute the shape of torch.aten.constant_pad_nd
uses negative indices when ...
25ba51b2af05a97ffa1b7af1cf584d193a3633f6 authored over 2 years ago by Maksim Levental <[email protected]>
eecbf0bab6ce5b0d5197a8e43485aa2896a708fb authored over 2 years ago by Maksim Levental <[email protected]>
520725cdc5aa3871423b107b000388dd17dcca5c authored over 2 years ago by Sean Silva <[email protected]>
The logic in the rewriting phase had a bug in case of a read-only op
coming before mutation ops....
52c330cca25d2da3847a920d02eefd25c8845aed authored over 2 years ago by Sean Silva <[email protected]>
3e999beaea0ff63f1e89d377d3f7c041513cd9b3 authored over 2 years ago by Maksim Levental <[email protected]>
That was back from an earlier stage in the project when e2e was a big
deal because we didn't hav...
0378c75b35a94f8fbbd3b7e01f1471489d2b77bf authored over 2 years ago by Sean Silva <[email protected]>
- update diagram to use the name "Eager Mode" instead of
`torch.dispatch`, which wasn't a very...
8383497704cf96dfe771983f2b2e4f1038de0612 authored over 2 years ago by Ahmed S. Taei <[email protected]>