Skip to content

Add AMD GPU test for ray clusters #670

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Mar 20, 2025
Merged

Add AMD GPU test for ray clusters #670

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
3 changes: 2 additions & 1 deletion .github/workflows/e2e_tests.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -89,7 +89,8 @@ jobs:
export CODEFLARE_TEST_OUTPUT_DIR=${{ env.TEMP_DIR }}

set -euo pipefail
go test -timeout 120m -v -skip "^Test.*Cpu$" ./test/e2e -json 2>&1 | tee ${CODEFLARE_TEST_OUTPUT_DIR}/gotest.log | gotestfmt
go test -timeout 120m -v -skip "^Test.*Cpu$|^Test.*ROCmGpu$" ./test/e2e -json 2>&1 | tee ${CODEFLARE_TEST_OUTPUT_DIR}/gotest.log | gotestfmt


- name: Print CodeFlare operator logs
if: always() && steps.deploy.outcome == 'success'
Expand Down
2 changes: 1 addition & 1 deletion go.mod
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,7 +11,7 @@ require (
github.com/openshift/api v0.0.0-20240904015708-69df64132c91
github.com/openshift/client-go v0.0.0-20240904130219-3795e907a202
github.com/project-codeflare/appwrapper v1.0.4
github.com/project-codeflare/codeflare-common v0.0.0-20250306164418-eb812487be82
github.com/project-codeflare/codeflare-common v0.0.0-20250317102908-1c124db97844
github.com/ray-project/kuberay/ray-operator v1.2.2
go.uber.org/zap v1.27.0
golang.org/x/exp v0.0.0-20240719175910-8a7402abbf56
Expand Down
4 changes: 2 additions & 2 deletions go.sum
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -225,8 +225,8 @@ github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRI
github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
github.com/project-codeflare/appwrapper v1.0.4 h1:364zQLX0tsi4LvBBYNKZL7PPbNWPbVU7vK6+/kVV/FQ=
github.com/project-codeflare/appwrapper v1.0.4/go.mod h1:A1b6bMFNMX5Btv3ckgeuAHVVZzp1G30pSBe6BE/xJWE=
github.com/project-codeflare/codeflare-common v0.0.0-20250306164418-eb812487be82 h1:cL1K2+r1lJVwBkhXiVFr2A9DphnylJmilYDIqg/W62M=
github.com/project-codeflare/codeflare-common v0.0.0-20250306164418-eb812487be82/go.mod h1:DPSv5khRiRDFUD43SF8da+MrVQTWmxNhuKJmwSLOyO0=
github.com/project-codeflare/codeflare-common v0.0.0-20250317102908-1c124db97844 h1:hEjZ2pV4Fp81wytijJZ7uHWovKIqirVBA/t1F5hIrbA=
github.com/project-codeflare/codeflare-common v0.0.0-20250317102908-1c124db97844/go.mod h1:DPSv5khRiRDFUD43SF8da+MrVQTWmxNhuKJmwSLOyO0=
github.com/prometheus/client_golang v1.20.5 h1:cxppBPuYhUnsO6yo/aoRol4L7q7UFfdm+bR9r+8l63Y=
github.com/prometheus/client_golang v1.20.5/go.mod h1:PIEt8X02hGcP8JWbeHyeZ53Y/jReSnHgO035n//V5WE=
github.com/prometheus/client_model v0.0.0-20190812154241-14fe0d1b01d4/go.mod h1:xMI15A0UPsDsEKsMN9yxemIoYk6Tm2C1GtYGdfGttqA=
Expand Down
2 changes: 1 addition & 1 deletion test/e2e/deployment_appwrapper_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -45,7 +45,7 @@ func TestDeploymentAppWrapper(t *testing.T) {
defer func() {
_ = test.Client().Kueue().KueueV1beta1().ResourceFlavors().Delete(test.Ctx(), resourceFlavor.Name, metav1.DeleteOptions{})
}()
clusterQueue := createClusterQueue(test, resourceFlavor, 0)
clusterQueue := createClusterQueue(test, resourceFlavor, CPU)
defer func() {
_ = test.Client().Kueue().KueueV1beta1().ClusterQueues().Delete(test.Ctx(), clusterQueue.Name, metav1.DeleteOptions{})
}()
Expand Down
2 changes: 1 addition & 1 deletion test/e2e/job_appwrapper_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,7 +43,7 @@ func TestBatchJobAppWrapper(t *testing.T) {
defer func() {
_ = test.Client().Kueue().KueueV1beta1().ResourceFlavors().Delete(test.Ctx(), resourceFlavor.Name, metav1.DeleteOptions{})
}()
clusterQueue := createClusterQueue(test, resourceFlavor, 0)
clusterQueue := createClusterQueue(test, resourceFlavor, CPU)
defer func() {
_ = test.Client().Kueue().KueueV1beta1().ClusterQueues().Delete(test.Ctx(), clusterQueue.Name, metav1.DeleteOptions{})
}()
Expand Down
10 changes: 5 additions & 5 deletions test/e2e/mnist_pytorch_appwrapper_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,15 +32,15 @@ import (
)

func TestMnistPyTorchAppWrapperCpu(t *testing.T) {
runMnistPyTorchAppWrapper(t, "cpu", 0)
runMnistPyTorchAppWrapper(t, CPU)
}

func TestMnistPyTorchAppWrapperGpu(t *testing.T) {
runMnistPyTorchAppWrapper(t, "gpu", 1)
runMnistPyTorchAppWrapper(t, NVIDIA)
}

// Trains the MNIST dataset as a batch Job in an AppWrapper, and asserts successful completion of the training job.
func runMnistPyTorchAppWrapper(t *testing.T, accelerator string, numberOfGpus int) {
func runMnistPyTorchAppWrapper(t *testing.T, accelerator Accelerator) {
test := With(t)

// Create a namespace
Expand All @@ -51,7 +51,7 @@ func runMnistPyTorchAppWrapper(t *testing.T, accelerator string, numberOfGpus in
defer func() {
_ = test.Client().Kueue().KueueV1beta1().ResourceFlavors().Delete(test.Ctx(), resourceFlavor.Name, metav1.DeleteOptions{})
}()
clusterQueue := createClusterQueue(test, resourceFlavor, numberOfGpus)
clusterQueue := createClusterQueue(test, resourceFlavor, accelerator)
defer func() {
_ = test.Client().Kueue().KueueV1beta1().ClusterQueues().Delete(test.Ctx(), clusterQueue.Name, metav1.DeleteOptions{})
}()
Expand Down Expand Up @@ -109,7 +109,7 @@ func runMnistPyTorchAppWrapper(t *testing.T, accelerator string, numberOfGpus in
{Name: "MNIST_DATASET_URL", Value: GetMnistDatasetURL()},
{Name: "PIP_INDEX_URL", Value: GetPipIndexURL()},
{Name: "PIP_TRUSTED_HOST", Value: GetPipTrustedHost()},
{Name: "ACCELERATOR", Value: accelerator},
{Name: "ACCELERATOR", Value: accelerator.Type},
},
Command: []string{"/bin/sh", "-c", "pip install -r /test/requirements.txt && torchrun /test/mnist.py"},
VolumeMounts: []corev1.VolumeMount{
Expand Down
Loading