File tree Expand file tree Collapse file tree 1 file changed +56
-0
lines changed Expand file tree Collapse file tree 1 file changed +56
-0
lines changed Original file line number Diff line number Diff line change 1+ name : Build Checks
2+ on : [push, pull_request]
3+ permissions :
4+ contents : read
5+ pull-requests : read
6+
7+ jobs :
8+ tuner-decisions-check :
9+ runs-on : ubuntu-22.04
10+ steps :
11+ - name : Install Dependencies
12+ run : |
13+ sudo apt-key del 7fa2af80
14+ wget https://developer.download.nvidia.com/compute/cuda/repos/ubuntu2204/x86_64/cuda-keyring_1.1-1_all.deb
15+ sudo dpkg -i cuda-keyring_1.1-1_all.deb
16+ sudo apt-get update
17+ sudo apt-get install cuda-toolkit libhwloc-dev
18+ pip install uv
19+
20+
21+ - name : Fetch and Install EFA Installer
22+ run : |
23+ curl -O https://efa-installer.amazonaws.com/aws-efa-installer-latest.tar.gz
24+ tar -xf aws-efa-installer-*.tar.gz
25+ pushd aws-efa-installer/
26+ sudo ./efa_installer.sh -y --skip-kmod
27+ popd
28+
29+ - uses : actions/checkout@v4
30+ - name : Build Plugin
31+ run : |
32+ set -x
33+
34+ # actions/checkout@v4 would drop the plugin source in $PWD,
35+ # so go ahead and build it.
36+ ./autogen.sh
37+ ./configure --with-mpi=/opt/amazon/openmpi \
38+ --with-libfabric=/opt/amazon/efa \
39+ --with-cuda=/usr/local/cuda/ \
40+ --enable-platform-aws \
41+ --prefix=$PWD/install
42+ make -j 2
43+ make install
44+
45+ - name : Tuner Check
46+ run : |
47+ pushd contrib/python/
48+
49+ OFI_NCCL_FORCE_PRODUCT_NAME=p5en.48xlarge uv run show-tuner-decisions ../..//install/lib/libnccl-ofi-tuner.so \
50+ --min-ranks-per-node 1 --max-ranks-per-node 8 \
51+ --min-nnodes 2 --max-nnodes 2048
52+
53+ OFI_NCCL_FORCE_PRODUCT_NAME=p5.48xlarge uv run show-tuner-decisions ../..//install/lib/libnccl-ofi-tuner.so \
54+ --min-ranks-per-node 1 --max-ranks-per-node 8 \
55+ --min-nnodes 2 --max-nnodes 2048
56+ popd
You can’t perform that action at this time.
0 commit comments