Open deep learning compiler stack for cpu, gpu and specialized accelerators

Clone this repo:
  1. d6622a3 Remove unused pylint 1.9.4 from docker installation script (#6538) by Leandro Nunes · 3 hours ago master
  2. 2621554 [Relay] Show yolo detection result in text. (#6367) by Hua Jiang · 7 hours ago
  3. b6e6395 [BYOC][ACL] Add maximum support for float32 (#6506) by Giuseppe Rossini · 7 hours ago
  4. 56b18ec [Ansor] Parallel the InitPopulation (#6529) by Chenfan · 8 hours ago
  5. cc96117 [FIX] fix the python script for building resnet (#6526) (#6527) by Shuwei Liu · 8 hours ago

Open Deep Learning Compiler Stack

Documentation | Contributors | Community | Release Notes

Build Status WinMacBuild

Apache TVM (incubating) 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.


© Contributors Licensed under an Apache-2.0 license.

Contribute to TVM

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 learned a lot from the following projects when building TVM.

  • Halide: Part of TVM's TIR and arithmetic simplification module originates from Halide. We also learned and adapted some part of lowering pipeline from Halide.
  • Loopy: use of integer set analysis and its loop transformation primitives.
  • Theano: the design inspiration of symbolic scan operator for recurrence.