Skip to content

Commit 5d631e3

Browse files
committed
fix: added script for installation of software
Signed-off-by: Akash Jaiswal <akashjaiswal3846@gmail.com>
1 parent 901bc75 commit 5d631e3

File tree

3 files changed

+40
-0
lines changed

3 files changed

+40
-0
lines changed

.github/workflows/test-e2e-gpu.yaml

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -44,6 +44,11 @@ jobs:
4444
pip install papermill==2.6.0 jupyter==1.1.1 ipykernel==6.29.5
4545
pip install git+https://github.com/kubeflow/sdk.git@main
4646
47+
- name: Setup the ephermal VM with software
48+
working-directory: ${{ env.GOPATH }}/src/github.com/kubeflow/trainer
49+
run: |
50+
make test-e2e-gpu-install-software
51+
4752
- name: Setup cluster with GPU support using nvidia/kind
4853
working-directory: ${{ env.GOPATH }}/src/github.com/kubeflow/trainer
4954
run: |

Makefile

Lines changed: 4 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -202,6 +202,10 @@ test-e2e-setup-cluster: kind ## Setup Kind cluster for e2e test.
202202
test-e2e-setup-gpu-cluster: kind ## Setup Kind cluster for GPU e2e test.
203203
KIND=$(KIND) K8S_VERSION=$(K8S_VERSION) ./hack/e2e-setup-gpu-cluster.sh
204204

205+
.PHONY: test-e2e-gpu-install-software
206+
test-e2e-gpu-install-software: ## Install software for GPU e2e test.
207+
./hack/e2e-gpu-arc-software.sh
208+
205209
.PHONY: test-e2e
206210
test-e2e: ginkgo ## Run Go e2e test.
207211
$(GINKGO) -v ./test/e2e/...

hack/e2e-gpu-install-software.sh

Lines changed: 31 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,31 @@
1+
# Installing nvidia toolkit
2+
echo "Install nvidia-ctk tool"
3+
4+
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \
5+
&& curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \
6+
sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \
7+
sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
8+
9+
sudo apt-get update
10+
11+
export NVIDIA_CONTAINER_TOOLKIT_VERSION=1.17.8-1
12+
sudo apt-get install -y \
13+
nvidia-container-toolkit=${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
14+
nvidia-container-toolkit-base=${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
15+
libnvidia-container-tools=${NVIDIA_CONTAINER_TOOLKIT_VERSION} \
16+
libnvidia-container1=${NVIDIA_CONTAINER_TOOLKIT_VERSION}
17+
18+
# Install nvkind
19+
echo "Install nvkind"
20+
sudo go install github.com/NVIDIA/nvkind/cmd/nvkind@latest
21+
22+
# Few Testing commands
23+
go version
24+
which nvkind
25+
26+
# Alias kubectl, kind, helm, nvkind with sudo
27+
alias docker="sudo docker"
28+
alias kubectl="sudo kubectl"
29+
alias kind="sudo kind"
30+
alias helm="sudo helm"
31+
alias nvkind="sudo nvkind"

0 commit comments

Comments
 (0)