commit | 9bc653219a3611a2e79404c59a90ea31755874ce | [log] [tgz] |
---|---|---|
author | Tianqi Chen <tqchen@users.noreply.github.com> | Mon Feb 20 11:38:22 2023 -0500 |
committer | GitHub <noreply@github.com> | Mon Feb 20 11:38:22 2023 -0500 |
tree | 5e4cfc7d52899eb1c0707f24b2f9b7d455435e5a | |
parent | 1d9863470e0e97413d05b98f2852dc7de60611a0 [diff] |
[BugFix][UMA] Protect target registration (#13624) (#14057) [BugFix][UMA] Protect target registration (#13624) (#4) This PR address fixes for UMA target registration. * Fix the doc issue #13304 * Continues stalled PR #12731 Changes: * Incorporates all proposed fixes from mentioned [PR #12731](https://github.com/apache/tvm/pull/12731) * Address test case concerns and discussions from [PR #12731](https://github.com/apache/tvm/pull/12731) * **NEW:** Already exiting target cannot be created, explicit error on this. * **NEW:** Attributes having special/reserved scope cannot be created explicitly. It also address proper test cases for all the above. Signed-off-by: tqchen <tianqi.tchen@gmail.com> Co-authored-by: Balint Cristian <cristian.balint@gmail.com>
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.