From 45fb0db6eb73312857a46a1484b6d09169ac5c94 Mon Sep 17 00:00:00 2001 From: Tariq Ibrahim Date: Mon, 6 Jul 2026 17:58:50 -0700 Subject: [PATCH] add new deploy label to manage third-party gpu client pods Signed-off-by: Tariq Ibrahim --- assets/state-mig-manager/0210_clusterrole.yaml | 6 ++++++ controllers/state_manager.go | 3 +++ 2 files changed, 9 insertions(+) diff --git a/assets/state-mig-manager/0210_clusterrole.yaml b/assets/state-mig-manager/0210_clusterrole.yaml index 2e9e9e8b90..c68c371bca 100644 --- a/assets/state-mig-manager/0210_clusterrole.yaml +++ b/assets/state-mig-manager/0210_clusterrole.yaml @@ -13,3 +13,9 @@ rules: - watch - update - patch +- apiGroups: + - "" + resources: + - pods + verbs: + - list diff --git a/controllers/state_manager.go b/controllers/state_manager.go index 37691059c1..6f0eb67432 100644 --- a/controllers/state_manager.go +++ b/controllers/state_manager.go @@ -94,6 +94,7 @@ var gpuStateLabels = map[string]map[string]string{ "nvidia.com/gpu.deploy.dcgm-exporter": "true", "nvidia.com/gpu.deploy.node-status-exporter": "true", "nvidia.com/gpu.deploy.operator-validator": "true", + "nvidia.com/gpu.deploy.client": "true", }, gpuWorkloadConfigVMPassthrough: { "nvidia.com/gpu.deploy.sandbox-device-plugin": "true", @@ -101,6 +102,7 @@ var gpuStateLabels = map[string]map[string]string{ "nvidia.com/gpu.deploy.vfio-manager": "true", "nvidia.com/gpu.deploy.kata-manager": "true", "nvidia.com/gpu.deploy.cc-manager": "true", + "nvidia.com/gpu.deploy.client": "true", }, gpuWorkloadConfigVMVgpu: { "nvidia.com/gpu.deploy.sandbox-device-plugin": "true", @@ -108,6 +110,7 @@ var gpuStateLabels = map[string]map[string]string{ "nvidia.com/gpu.deploy.vgpu-device-manager": "true", "nvidia.com/gpu.deploy.sandbox-validator": "true", "nvidia.com/gpu.deploy.cc-manager": "true", + "nvidia.com/gpu.deploy.client": "true", }, }