forked from jiuyuan/InfiniTensor
11d5aa1ccc
* Add: interface for membound TVM kernel and test * add getAnsorCode * add evaluation, but link failed * add evaluation of kernel, but link failed * Fix: link libcuda and nvrtc * add print * Add: const for source of copy * compile and evaluate the kernel * add compute * fix gen_ansor_op.py * fix membound_TVM * format and fix CMakeLists.txt * fix memory leak Co-authored-by: Liyan Zheng <liyan-zheng@outlook.com> Co-authored-by: huangshuhong <huangsh19@mails.tsinghua.edu.cn> |
||
---|---|---|
.github/workflows | ||
3rd-party | ||
include | ||
proto | ||
python/cpp_plugin | ||
src | ||
test | ||
.clang-format | ||
.cmake-format.json | ||
.gitignore | ||
.gitmodules | ||
CMakeLists.txt | ||
LICENSE | ||
README.md |
README.md
InfiniTensor
Compilation on Lotus
# Enter the root of InfiniTensor
source test/script/env_lotus.sh
mkdir build && cd build
cmake -DUSE_CUDA=ON .. && make -j 12
Contributor Guide
InfiniTensor development is based on the pull request on Github. Before requesting for merging, a PR should satisfy the following requirements
- Pass all tests.
- Currently, CI on Github only checks code format. Script
test/script/clang_format_inplace.sh
is for formatting all code. - Contributors should run
ctest
manually and copy its output to the PR. Use fenced code blocks (triple backquotes, i.e.,```
) to avoid referencing in Github. Otherwise,#
in the output is interpreted as a Github reference. Do not directly paste the ctest output in commit messages either for the same reason.
- Currently, CI on Github only checks code format. Script
- Receive at least one approval from reviewers.
- PR title should be concise since it is going to be the commit message in the main branch after merging and squashing.