microsoft
/
onnxruntime-tvm
зеркало из https://github.com/microsoft/onnxruntime-tvm.git
1
0
Форкнуть 0
Код Задачи Пакеты Проекты Релизы Вики Активность
Open deep learning compiler stack for cpu, gpu and specialized accelerators
332 коммитов 8 Ветки 5 Теги 18 MiB
Python 49.8%
C++ 41.1%
Scala 1.4%
Rust 1.4%
Java 1.3%
Разное 4.9%
Перейти к файлу
ziheng 1389d20888 [EXECUTOR] Split graph_executor to header file and (runtime) source file (#300) 
* [EXECUTOR] Split graph_executor to header file and (runtime) source file

* Fix
 		2017-08-05 20:30:40 -07:00
HalideIR@326e2fa187 [EXECUTOR] Add GraphHandle (#285) 2017-07-28 16:20:52 -07:00
apps [EXECUTOR] Split graph_executor to header file and (runtime) source file (#300) 2017-08-05 20:30:40 -07:00
cmake use auto source_group (#146) 2017-05-18 09:17:47 -07:00
dlpack@36e573893f [MODULE/RUNTIME] Remove Precompile, simplify module (#174) 2017-06-05 22:00:22 -07:00
dmlc-core@7afa45b87c [DOC] Fix doxygen comments (#247) 2017-07-14 17:33:40 -07:00
docs [SCHEDULE][RUNIME] Introduce pragma for additional extension hint, threadpool runtime. (#299) 2017-08-05 15:37:22 -07:00
include/tvm [SCHEDULE][RUNIME] Introduce pragma for additional extension hint, threadpool runtime. (#299) 2017-08-05 15:37:22 -07:00
jvm [TEST] Fix java compilation (#279) 2017-07-27 08:33:32 -07:00
make [DOC] More detailed installation instruction (#262) 2017-07-18 22:42:02 -07:00
python [SCHEDULE][RUNIME] Introduce pragma for additional extension hint, threadpool runtime. (#299) 2017-08-05 15:37:22 -07:00
src [SCHEDULE][RUNIME] Introduce pragma for additional extension hint, threadpool runtime. (#299) 2017-08-05 15:37:22 -07:00
tests [SCHEDULE][RUNIME] Introduce pragma for additional extension hint, threadpool runtime. (#299) 2017-08-05 15:37:22 -07:00
topi [SCHEDULE][REFACTOR] Default Fuse to outer inner, consistent to split (#289) 2017-07-31 17:57:18 -07:00
tutorials/python Conda build recipe (#288) 2017-08-01 15:23:56 -07:00
verilog [CONTRIB/BLAS] Add CBLAS Example to contrib (#120) 2017-05-05 10:55:34 -07:00
web [SCHEDULE][RUNIME] Introduce pragma for additional extension hint, threadpool runtime. (#299) 2017-08-05 15:37:22 -07:00
.gitignore gitignore tags (#277) 2017-07-27 08:33:38 -07:00
.gitmodules License as BSD for now before we finish approval for apache (#118) 2017-05-04 15:34:01 -07:00
.travis.yml Remove linux from travis (#156) 2017-05-22 19:47:12 -07:00
CMakeLists.txt Conda build recipe (#288) 2017-08-01 15:23:56 -07:00
CONTRIBUTORS.md [TUTORIAL] Optimize gemm on CPU add! (#270) 2017-07-25 22:58:41 -07:00
Jenkinsfile [WIP][Frontend] Scala/Java package (#176) 2017-07-14 23:04:39 -07:00
LICENSE [DOC/LICENSE] Make doc and license consistent, opensource repo when we get approval (#134) 2017-05-09 20:36:23 -07:00
Makefile Build system and dynamic library fixes (#283) 2017-07-31 12:23:34 -07:00
NEWS.md [DOC/LICENSE] Make doc and license consistent, opensource repo when we get approval (#134) 2017-05-09 20:36:23 -07:00
README.md [DOCS] Jenkins deployment of docs, add FAQ (#157) 2017-05-23 23:26:22 -07:00

README.md

GitHub license Build Status

Installation | Documentation | Tutorials | FAQ | Contributors | Release Notes

TVM

TVM is a low level domain specific language(DSL) for compiling tensor computation pipelines. It is designed to compile multi-dimensional tensor algebra pipelines which are crucial to deep learning frameworks.

Contribute to TVM

Your help is very valuable to make the package better for everyone.

Documentation

The current documentation can be build locally via sphinx. See docs folder for details.