commit | 622bd150dd331780eb41a1c67c65aae802eb9b20 | [log] [tgz] |
---|---|---|
author | Eric Lunderberg <Lunderberg@users.noreply.github.com> | Thu Apr 18 16:41:59 2024 -0500 |
committer | GitHub <noreply@github.com> | Thu Apr 18 16:41:59 2024 -0500 |
tree | 7a222c7b41ccbee504b941c2347898a4c45885ac | |
parent | fe5270956de7198bea6bdc53a1bd4202e836b829 [diff] |
[Relax] Handle binary operations between Tensor and PrimValue (#16827) * [Relax] Handle binary operations between Tensor and PrimValue Prior to this commit, binary operations were only defined between two tensors. This commit allows binary operations to apply between a tensor and a `relax::PrimValue`. When inferring the output `StructInfo`, binary operations with a `PrimValue` produce the same output as using a 0-d tensor. When legalizing operations containing a `PrimValue`, they are lowered to primitive TIR arguments. * Fix unit tests * Restore ICHECK for scalar TIR variable * Fix a few more unit tests * Remove handling of ObjectStructInfo * Undo commenting-out of test cases * Update for improved error messages * Fix failing unit tests * Fix unit test
Documentation | Contributors | Community | Release Notes
Apache TVM is a compiler stack for deep learning systems. It is designed to close the gap between the productivity-focused deep learning frameworks, and the performance- and efficiency-focused hardware backends. TVM works with deep learning frameworks to provide end to end compilation to different backends.
TVM is licensed under the Apache-2.0 license.
Check out the TVM Documentation site for installation instructions, tutorials, examples, and more. The Getting Started with TVM tutorial is a great place to start.
TVM adopts apache committer model, we aim to create an open source project that is maintained and owned by the community. Check out the Contributor Guide.
We learned a lot from the following projects when building TVM.