dmlc--dgl
d460efee3e
* add bench jenkins * instance type * fix * fix * fix * 111 * test * 111 * 111 * fix * test * run * fix * fix * fix * fix * fix * publish results * 111 * regression * launch ec2 script * fix * add * run on master * change * rrr * run gpu * fix * fix * try fix * fix * ff * fix * fix * fix * refactor * fix * fix * update * fix * fix * fix * fix * remove import torchtext * add shm size * update * fix * fix * fix * fix * fix this!!!! * 111 * fix * remove verbose * fix * fix * fix * fix * fix * fix * fix * fix * update readme * fix * fix * fix * change asv default to head * commit sage and rgcn * fix * update * add benchmarks * add * fix * update * remove RandomState * tmp remove * new batch * fix * fix * fix * address comment * fix warning * fix * fix * fix * fix * add multiupdate all * address comment * fix * add benchmarks * add * fix timing * fix * push * add -v * [Example] NGCF (#2564) * ngcf * ngcf * update Co-authored-by: zhjwy9343 <6593865@qq.com> * Revert "[Example] NGCF (#2564)" (#2611) This reverts commit a75e04f408c719289f478ca129784e05655d8def. * fix * change task * fix * fix * fix2 * enable tensoradapter when benchmark * minor fix * trigger ci * fix * fix Co-authored-by: Minjie Wang <wmjlyjemaine@gmail.com> Co-authored-by: KounianhuaDu <51199171+KounianhuaDu@users.noreply.github.com> Co-authored-by: zhjwy9343 <6593865@qq.com>
23 行
382 B
Bash
23 行
382 B
Bash
#!/bin/bash
|
|
|
|
set -e
|
|
|
|
. /opt/conda/etc/profile.d/conda.sh
|
|
conda activate pytorch-ci
|
|
# Default building only with cpu
|
|
DEVICE=${DGL_BENCH_DEVICE:-cpu}
|
|
|
|
# build
|
|
if [[ $DEVICE == "cpu" ]]; then
|
|
CMAKE_VARS=""
|
|
else
|
|
CMAKE_VARS="-DUSE_CUDA=ON"
|
|
fi
|
|
mkdir -p build
|
|
pushd build
|
|
cmake -DCUDA_TOOLKIT_ROOT_DIR=/usr/local/cuda -DBUILD_TORCH=ON $CMAKE_VARS ..
|
|
make -j
|
|
popd
|
|
|
|
conda deactivate
|