tag | 6b753e16cb9fc41ce5952b7439aff5f2d3e519b6 | |
---|---|---|
tagger | Siyuan Feng <hzfengsy@sjtu.edu.cn> | Mon Apr 10 13:13:56 2023 +0800 |
object | 15f9be5449a1a351b65f327a3a5e2aaf578a7161 |
commit | 15f9be5449a1a351b65f327a3a5e2aaf578a7161 | [log] [tgz] |
---|---|---|
author | Chaofan Lin <1713833595@qq.com> | Sun Apr 09 20:13:57 2023 +0800 |
committer | GitHub <noreply@github.com> | Sun Apr 09 08:13:57 2023 -0400 |
tree | 5ee331ac0848d28dfd9d06445cecd6ea221f3f88 | |
parent | a84a2cbe07dfe608acd79453affc53330ebab1f0 [diff] |
[TOPI] Expose `topi::collapse_sum` to Python and support symbolic shape (#14541) TOPI has an implementation of collapse_sum internally (tvm/topi/reduction.h) but it is not exposed to FFI and can not be called in Python side. This patch exposes it and adds related tests. And this PR lets the implementation of topi::collapse_sum support symbolic shape cases.
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.