Skip to content
main
Switch branches/tags
7 branches 8 tags
Code

Latest commit

@masahi
masahi [CUTLASS] Support batch_matmul (#9439)
c7a01a4 Nov 4, 2021
[CUTLASS] Support batch_matmul (#9439) 
* Import batched gemm change

commit cfacfa2
Author: Masahiro Masuda <masahi129@gmail.com>
Date:   Mon Nov 1 15:57:49 2021 +0900

    change is_constant pattern to wildcard in gelu pattern

commit 84da943
Author: Masahiro Masuda <masahi129@gmail.com>
Date:   Mon Nov 1 05:41:11 2021 +0900

    fixed batch stride C

commit 66e5779
Author: Masahiro Masuda <masahi129@gmail.com>
Date:   Sun Oct 31 20:47:16 2021 +0900

    refactoring codegen

commit 561daea
Author: Masahiro Masuda <masahi129@gmail.com>
Date:   Sun Oct 31 20:05:20 2021 +0900

    generated kernel compiled and result match

commit a5740bc
Author: Masahiro Masuda <masahi129@gmail.com>
Date:   Sun Oct 31 19:36:53 2021 +0900

    partitioning looks good

commit 59112fd
Author: Masahiro Masuda <masahi129@gmail.com>
Date:   Sun Oct 31 19:01:47 2021 +0900

    [WIP] cutlass batch matmul support

* fixed test

* refactoring

* gelu test fixed

* more refactor

* batch_matmul fp32 accum working

* dynamic batch matmul working

* black

* remove doc TODO
c7a01a4

Git stats

Files

Permalink
Failed to load latest commit information.
Type
Name
Latest commit message
Commit time
.github
change id (#9431)
Nov 2, 2021
3rdparty
[BYOC] CUTLASS integration (#9261)
Oct 29, 2021
apps
[microTVM] Add microTVM Template Projects to tlcpack pip Package (#9309)
Nov 1, 2021
cmake
[microTVM] Add microTVM Template Projects to tlcpack pip Package (#9309)
Nov 1, 2021
conda
[FIX] Remove leftover instances of USE_GRAPH_EXECUTOR_DEBUG (#8796)
Aug 24, 2021
docker
Bump the CMake version in ubuntu_install_cmake_source.sh to 3.14.7. (#…
Nov 2, 2021
docs
[DOC] Add tip on mitigation for symbol conflict with PyTorch (#9433)
Nov 2, 2021
gallery
[microTVM] Add microTVM Template Projects to tlcpack pip Package (#9309)
Nov 1, 2021
golang
Fix #8510 (#8511)
Jul 27, 2021
include/tvm
Adds SEScope (Storage/Execution Scope) for use as new unit of plannin…
Nov 3, 2021
jvm
[FIX] Remove leftover instances of USE_GRAPH_EXECUTOR_DEBUG (#8796)
Aug 24, 2021
licenses
[BYOC] CUTLASS integration (#9261)
Oct 29, 2021
nnvm
Fixed minor misspelling (#7499)
Feb 22, 2021
python
[CUTLASS] Support batch_matmul (#9439)
Nov 4, 2021
rust
Fix CallNode Rust binding (#9381)
Nov 1, 2021
src
[CUTLASS] Support batch_matmul (#9439)
Nov 4, 2021
tests
[CUTLASS] Support batch_matmul (#9439)
Nov 4, 2021
vta
Fix direct and broken links (#9314)
Oct 19, 2021
web
[Refactor] Rename .asnumpy() to .numpy() (#8659)
Aug 8, 2021
.asf.yaml
Test run triage (#9308)
Oct 18, 2021
.clang-format
add .clang-format (#2395)
Jan 8, 2019
.gitignore
[Keras] Add l2_normalize support (#9383)
Nov 3, 2021
.gitmodules
[BYOC] CUTLASS integration (#9261)
Oct 29, 2021
.pre-commit-config.yaml
[CI] make pre-commit hooks to run on every push instead of every comm…
Aug 31, 2021
CMakeLists.txt
[microTVM] Add microTVM Template Projects to tlcpack pip Package (#9309)
Nov 1, 2021
CONTRIBUTORS.md
add reviewer (#9430)
Nov 2, 2021
Jenkinsfile
fix (#9412)
Nov 1, 2021
KEYS
Zhi's key for ASF release (#6554)
Sep 26, 2020
LICENSE
[BYOC] CUTLASS integration (#9261)
Oct 29, 2021
Makefile
Force CMake targets in top-level Makefile to run (#8840)
Aug 25, 2021
NEWS.md
[microTVM] Refactor uTVM to microTVM (#8283)
Jun 22, 2021
NOTICE
[DOCS] Remove incubating from docs (#7525)
Feb 25, 2021
README.md
[Tutorial] Fix formatting, grammar, dead link (#9281)
Oct 23, 2021
conftest.py
[UnitTests] Expose TVM pytest helpers as plugin (#8532)
Aug 27, 2021
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
Removed a manual file handler pitfall (#9435)
Nov 3, 2021
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

Releases 9

Apache TVM (incubating) v0.7.0 Latest
Oct 2, 2020
+ 8 releases

Packages

No packages published

Contributors 615

+ 604 contributors

Languages