commit | 3d53ef3cfb93fe595465564d161d85fd13e7ee45 | [log] [tgz] |
---|---|---|
author | ziheng <ziheng@apache.org> | Sat Feb 16 03:44:01 2019 -0800 |
committer | ZihengJiang <ziheng@apache.org> | Mon Feb 18 14:42:45 2019 -0800 |
tree | 27e02d3e86ea7f12466cb3b56e764ea414dec65d | |
parent | 2e5ca24c769799bbef359d59eb4318f4baec52eb [diff] |
[Quantize] Skip for same input-output domain scale. (#2611) (cherry picked from commit 66cd036e2fa3f80ddf85ccea640ca405f5ac3eca)
Documentation | Contributors | Community | Release Notes
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. Checkout the tvm stack homepage for more information.
© Contributors Licensed under an Apache-2.0 license.
TVM adopts apache committer model, we aim to create an open source project that is maintained and owned by the community. Checkout the Contributor Guide
We learnt a lot from the following projects when building TVM.