Skip to content

apache/tvm

main
Switch branches/tags
26 branches 12 tags
Code

Latest commit

@mbs-octoml
mbs-octoml [Collage] CombinerRule and CandidatePartition::EstimateCost (#12078)
261de53 Jul 13, 2022
[Collage] CombinerRule and CandidatePartition::EstimateCost (#12078) 
* [Collage] CombinerRule and CandidatePartition::EstimateCost

See https://github.com/apache/tvm-rfcs/blob/main/rfcs/0062-collage.md.

We complete the PartitionRule sub-class hierarchy with the addition of
CombinePartitionRule, which allows disjoint candidate partitions to be
unioned based on simple rules.
 - By TOpPattern kind, eg a kOutElemwiseFusable and kBroadcast.
 - A tuple argument with injective fields.
 - The projection from an injective group (obviously of tuple type)
 - Combinations of the above.
These let us mimic many common fusion strategies, including TVMs, so that
the candidates explored during Collage search are as large as possible to
expose possible fusion opportunities but no larger.

Also completes CandidatePartition with the EstimateCost method, which is
used during search to construct a stand-alone IRModule for latency estimation.

Finish units tests for PartitionRule and CandidatePartition.

* - fix relay.collage ffi prefix.
261de53

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
.github
[ci] Add manual workflow to upload files to CI bucket (#11856)
Jun 24, 2022
3rdparty
Run cpplint in quiet mode. (#10292)
May 2, 2022
apps
[CMSIS_NN] Align CMSIS-NN in TVM to TFLu SHA (#12030)
Jul 13, 2022
ci
[ci] Don't skip index-triggered builds (#11915)
Jul 1, 2022
cmake
[BYOC] Handle constants in IRModule-at-a-time external codegen (#11770)
Jun 30, 2022
conda
[ci][actions] Add more HTTP retries for conda (#11360)
May 18, 2022
configs
[TVMC] Add --config argument for config files (#11012)
Apr 19, 2022
docker
[CMSIS_NN] Align CMSIS-NN in TVM to TFLu SHA (#12030)
Jul 13, 2022
docs
Add xgboost version restriction (#12050)
Jul 11, 2022
gallery
[docs][tvmc] Fix ResNet50 model URL (#12040)
Jul 12, 2022
golang
[TARGET] Move target_host usage to new target style. (#9497)
Nov 12, 2021
include/tvm
[Arith] Updated BufferDomainTouched to use IRVisitorWithAnalyzer (#1…
Jul 13, 2022
jvm
Remove javah support (#10104)
Feb 3, 2022
licenses
[BYOC] CUTLASS integration (#9261)
Oct 29, 2021
python
[TOPI, x86] Properly handle fused ops in TE softmax schedule (#12015)
Jul 13, 2022
rust
[RUST] Add conv3d transpose Rust bindings (#11471)
May 27, 2022
src
[Collage] CombinerRule and CandidatePartition::EstimateCost (#12078)
Jul 13, 2022
tests
[Collage] CombinerRule and CandidatePartition::EstimateCost (#12078)
Jul 13, 2022
vta
[Analysis] Exposed Analyzer::CanProveEqual to Python API (#11102)
Apr 22, 2022
web
Add cooldown interval logic for the profiling functional (#11465)
Jun 28, 2022
.asf.yaml
[ci] Switch to requiring pr-head for merges (#11081)
Apr 26, 2022
.clang-format
add .clang-format (#2395)
Jan 8, 2019
.gitattributes
[ci] Restructure Jenkinsfile (#11380)
May 20, 2022
.gitignore
[ci][docker] Fall back to tlcpackstaging if images don't exist (#11775)
Jun 23, 2022
.gitmodules
Fix submodule URLs. (#10888)
Apr 5, 2022
.pre-commit-config.yaml
[CI] make pre-commit hooks to run on every push instead of every comm…
Aug 31, 2021
CMakeLists.txt
[Collage] SubGraphs (#11981)
Jul 11, 2022
CONTRIBUTORS.md
[COMMUNITY] Hongyi Jin -> Reviewer (#11998)
Jul 2, 2022
Jenkinsfile
[ci] Don't skip index-triggered builds (#11915)
Jul 1, 2022
KEYS
[COMMUNITY] Add driazati key for release (#12076)
Jul 12, 2022
LICENSE
Update license file to note libbacktrace (#9579)
Nov 25, 2021
Makefile
Fix make format (#11197)
May 2, 2022
NEWS.md
convert full-width characters to half-width characters (#11112)
Apr 25, 2022
NOTICE
[DOCS] Remove incubating from docs (#7525)
Feb 25, 2021
README.md
[Tutorial] Fix formatting, grammar, dead link (#9281)
Oct 23, 2021
conftest.py
[CI] Added message if test is running on another shard (#11331)
May 18, 2022
mypy.ini
[MyPy] Minimal type checking on TIR schedule (#8367)
Jul 1, 2021
pyproject.toml
[Diagnostics][Relay][InferType] Refactor InferType to work on whole m…
Oct 9, 2020
version.py
This patch is to fix some minor typos in project. (#9852)
Jan 6, 2022
Open Deep Learning Compiler Stack License Getting Started Contribute to TVM Acknowledgement

README.md

Open Deep Learning Compiler Stack

Documentation | Contributors | Community | Release Notes

Build Status WinMacBuild

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.

License

TVM is licensed under the Apache-2.0 license.

Getting Started

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.

Contribute to TVM

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.

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

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

Resources

Readme

License

Apache-2.0 license

Code of conduct

Code of conduct

Stars

8.3k stars

Watchers

378 watching

Forks

2.6k forks

Releases 10

Apache TVM v0.8 Release Note Latest
Nov 24, 2021
+ 9 releases

Packages

No packages published

Contributors 721

+ 710 contributors

Languages