Skip to content

docs: use pGPU alias #2070

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
katexochen merged 1 commit into from
Jan 9, 2026
Merged

docs: use pGPU alias #2070

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
4 changes: 3 additions & 1 deletion docs/docs/howto/cluster-setup/bare-metal.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -205,6 +205,8 @@ helm install --wait --generate-name \
--set sandboxDevicePlugin.repository=ghcr.io/nvidia \
--set sandboxDevicePlugin.image=nvidia-sandbox-device-plugin \
--set sandboxDevicePlugin.version=8e76fe81 \
--set 'sandboxDevicePlugin.env[0].name=P_GPU_ALIAS' \
--set 'sandboxDevicePlugin.env[0].value=pgpu' \
--set nfd.enabled=true \
--set nfd.nodefeaturerules=true
```
Expand Down Expand Up @@ -296,7 +298,7 @@ The above command should yield an output similar to the following, depending on

```json
{
"nvidia.com/GH100_H100_PCIE": "1"
"nvidia.com/pgpu": "1"
}
```

Expand Down
2 changes: 1 addition & 1 deletion docs/docs/howto/workload-deployment/GPU-configuration.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -63,7 +63,7 @@ spec:
- # ...
resources:
limits:
"nvidia.com/GH100_H100_PCIE": 1
"nvidia.com/pgpu": 1
env:
# ...
- name: NVIDIA_VISIBLE_DEVICES
Expand Down
6 changes: 2 additions & 4 deletions e2e/gpu/gpu_test.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,19 +42,17 @@ func TestGPU(t *testing.T) {
runtimeHandler, err := manifest.RuntimeHandler(platform)
require.NoError(t, err)

var deviceURI, gpuName string
var gpuName string
switch platform {
case platforms.MetalQEMUTDXGPU:
deviceURI = "nvidia.com/GB100_B200"
gpuName = "NVIDIA B200"
case platforms.MetalQEMUSNPGPU:
deviceURI = "nvidia.com/GH100_H100_PCIE"
gpuName = "NVIDIA H100 PCIe"
default:
t.Errorf("platform %s does not support GPU tests", platform)
}

resources := kuberesource.GPU(deviceURI)
resources := kuberesource.GPU()

// Since the TDX-GPU testing cluster has multiple GPUs, we run into the drift
// explained in [1]. To avoid this, we need to remove the deployment of the direct GPU tester,
Expand Down
2 changes: 1 addition & 1 deletion internal/kuberesource/resourcegen/main.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -68,7 +68,7 @@ func main() {
case "vault":
subResources = kuberesource.PatchRuntimeHandlers(kuberesource.Vault(*namespace), "contrast-cc")
case "gpu":
subResources = kuberesource.PatchRuntimeHandlers(kuberesource.GPU("placeholder-gpu"), "contrast-cc")
subResources = kuberesource.PatchRuntimeHandlers(kuberesource.GPU(), "contrast-cc")
default:
log.Fatalf("Error: unknown set: %s\n", set)
}
Expand Down
4 changes: 2 additions & 2 deletions internal/kuberesource/sets.go
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -658,7 +658,7 @@ done
}

// GPU returns the resources for deploying a GPU test pod.
func GPU(deviceURI string) []any {
func GPU() []any {
tester := Deployment("gpu-tester", "").
WithSpec(DeploymentSpec().
WithReplicas(1).
Expand All @@ -679,7 +679,7 @@ func GPU(deviceURI string) []any {
WithResources(ResourceRequirements().
WithMemoryLimitAndRequest(500). // This accounts for nvidia-smi and the guest pull overhead.
WithLimits(corev1.ResourceList{
corev1.ResourceName(deviceURI): resource.MustParse("1"),
corev1.ResourceName("nvidia.com/pgpu"): resource.MustParse("1"),
}),
),
Container().
Expand Down
5 changes: 2 additions & 3 deletions packages/upgrade-gpu-operator.sh
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -50,9 +50,6 @@ kubectl delete crd nvidiadrivers.nvidia.com --ignore-not-found
helm repo add nvidia https://helm.ngc.nvidia.com/nvidia && helm repo update

# Upstream instructions from https://github.com/kata-containers/kata-containers/pull/12257
# The P_GPU_ALIAS environment variable is stripped to get per-GPU annotations for heterogenous
# clusters. With it, all GPUs will look like this to CDI clients: `nvidia.com/pgpu`. Without
# it, the annotations are specific to the GPU type: `nvidia.com/GB100_B200`.
helm install --wait --generate-name \
-n gpu-operator --create-namespace \
nvidia/gpu-operator \
Expand All @@ -72,6 +69,8 @@ helm install --wait --generate-name \
--set sandboxDevicePlugin.repository=ghcr.io/nvidia \
--set sandboxDevicePlugin.image=nvidia-sandbox-device-plugin \
--set sandboxDevicePlugin.version=8e76fe81 \
--set 'sandboxDevicePlugin.env[0].name=P_GPU_ALIAS' \
--set 'sandboxDevicePlugin.env[0].value=pgpu' \
--set nfd.enabled=true \
--set nfd.nodefeaturerules=true

Expand Down