e6420c7b36
Move all 88 service modules (66 individual + 22 platform) from modules/kubernetes/<service>/ into their corresponding stack directories: - Service stacks: stacks/<service>/module/ - Platform stack: stacks/platform/modules/<service>/ This collocates module source code with its Terragrunt definition. Only shared utility modules remain in modules/kubernetes/: ingress_factory, setup_tls_secret, dockerhub_secret, oauth-proxy. All cross-references to shared modules updated to use correct relative paths. Verified with terragrunt run --all -- plan: 0 adds, 0 destroys across all 68 stacks.
27 lines
796 B
YAML
27 lines
796 B
YAML
driver:
|
|
enabled: true
|
|
# repository: nvcr.io/nvidia/driver
|
|
# choose a driver version compatible with your GPU + CUDA 12.x (example)
|
|
# NVIDIA GPU driver - https://docs.nvidia.com/datacenter/cloud-native/gpu-operator/latest/platform-support.html#known-issue
|
|
# https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/
|
|
# 13.x >= 580
|
|
# 12.x >= 525, <580
|
|
# 11.x >= 450, <525
|
|
#
|
|
# Delete the cluster policy before each change
|
|
# version: "575.57.08" # CUDA 12.9
|
|
version: "570.195.03" # CUDA 12.8
|
|
upgradePolicy:
|
|
autoUpgrade: false
|
|
|
|
devicePlugin:
|
|
config:
|
|
name: time-slicing-config
|
|
|
|
# Tolerate GPU node taint for all GPU operator components
|
|
daemonsets:
|
|
tolerations:
|
|
- key: "nvidia.com/gpu"
|
|
operator: "Equal"
|
|
value: "true"
|
|
effect: "NoSchedule"
|