Skip to content

/ tvm

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

tvm.apache.org/
Apache-2.0 License
6k stars 1.7k forks
Star
Watch
main
5 branches 8 tags
Go to file
Code
Clone

Use Git or checkout with SVN using the web URL.

Latest commit

@masahi masa
masahi and masa [TOPI] GPU scatter 1D via sorting based approach (#7056)
465cd14 Dec 9, 2020
[TOPI] GPU scatter 1D via sorting based approach (#7056) 
* add thrust stable sort

* rename

* scatter via sort working

* correctly handles negative indices

* clean up, add some comments

* add doc string

* remove scatter benchmark stuff

* add more doc

* fix typo

* lint fix

* silence lint

* fix py format

* check for thrust availablity before test

Co-authored-by: masa <[email protected]>
465cd14

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
.github
[CI] Update actions miniconda (#6926)
Nov 16, 2020
3rdparty
[TOPI][OP] cuda for argwhere (#6868)
Dec 4, 2020
apps
[µTVM] Modify reference VMs to support new µTVM demo (#7001)
Dec 3, 2020
cmake
[TOPI] GPU scatter 1D via sorting based approach (#7056)
Dec 9, 2020
conda
[DOCS] Improve windows build instruction via conda (#6944)
Nov 21, 2020
docker
fix docker image when installing rust (#7004)
Dec 1, 2020
docs
[DOCS] Document cloudpickle dependency in tutorials (#7049)
Dec 8, 2020
golang
[REFACTOR] Remainings of util => utils (#6778)
Oct 29, 2020
include/tvm
[LLVM] Support atomic for GPU backend (NVPTX, ROCm) (#7051)
Dec 8, 2020
jvm
[DOCS] Update to reflect the repo name change (#6967)
Nov 24, 2020
licenses
Bring Your Own Datatypes (#5812)
Sep 26, 2020
nnvm
More CHECK to ICHECK (#6758)
Oct 26, 2020
python
[TOPI] GPU scatter 1D via sorting based approach (#7056)
Dec 9, 2020
rust
[DOCS] Update to reflect the repo name change (#6967)
Nov 24, 2020
src
[TOPI] GPU scatter 1D via sorting based approach (#7056)
Dec 9, 2020
tests
[TOPI] GPU scatter 1D via sorting based approach (#7056)
Dec 9, 2020
tutorials
[DOCS] Document cloudpickle dependency in tutorials (#7049)
Dec 8, 2020
vta
[DOCS] Document cloudpickle dependency in tutorials (#7049)
Dec 8, 2020
web
[DOCS] Update to reflect the repo name change (#6967)
Nov 24, 2020
.asf.yaml
[INFO] Add .asf.yaml for github info (#4761)
Jan 21, 2020
.clang-format
add .clang-format (#2395)
Jan 8, 2019
.gitignore
[CONDA] Revamp conda recipe. (#6732)
Oct 24, 2020
.gitmodules
[VTA] HW sources refactor (#5188)
Mar 31, 2020
CMakeLists.txt
[Hardware][Verilator] Integrating and simulating hardware accelerator…
Nov 29, 2020
CONTRIBUTORS.md
[DOCS] Update to reflect the repo name change (#6967)
Nov 24, 2020
DISCLAIMER
[COMMUNITY] Add DISCLAIMER, KEYS for ASF release (#4345)
Nov 15, 2019
Jenkinsfile
[FIX] Add task_ci_python_setup.sh to the arm CI (#6850)
Nov 5, 2020
KEYS
Zhi's key for ASF release (#6554)
Sep 26, 2020
LICENSE
Bring Your Own Datatypes (#5812)
Sep 26, 2020
Makefile
[CI] Move to use main as the default (#6665)
Oct 12, 2020
NEWS.md
[CI] Move to use main as the default (#6665)
Oct 12, 2020
NOTICE
Update date in the NOTICE (#5942)
Jun 27, 2020
README.md
[DOCS] Update to reflect the repo name change (#6967)
Nov 24, 2020
conftest.py
[Format] Convert all Python code w/o CI (#6448)
Sep 11, 2020
pyproject.toml
[Diagnostics][Relay][InferType] Refactor InferType to work on whole m…
Oct 9, 2020
pytest.ini
[TESTS] Refactor tests to run on either the GPU or CPU. (#6331)
Sep 2, 2020
version.py
[REFACTOR] Remainings of util => utils (#6778)
Oct 29, 2020

README.md

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.

License

© 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

Acknowledgement

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.

About

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

tvm.apache.org/

Topics

compiler tensor deep-learning gpu opencl metal performance javascript rocm tvm vulkan spirv machine-learning

Resources

Readme

License

Apache-2.0 License

Releases 8

Apache TVM (incubating) v0.7.0 Latest
Oct 2, 2020
+ 7 releases

Packages

No packages published

Contributors 458

+ 447 contributors

Languages

You can’t perform that action at this time.