10d81b0703
Remove orphaned `ci` pool (GP1-XS, 4 vCPU wasted — nothing scheduled to it). Remove `ci-build` pool (GP1-M) — builds now run on gpu-training (H100-1-80G: 24 vCPU, 240GB, real CUDA). This eliminates the need for CUDA stubs, separate test-gpu jobs, and ml crate exclusions. Pool layout after: always-on DEV1-M (core services, always on) gitlab GP1-XS (GitLab CE + runner manager, always on) gpu-training H100-1-80G (CI builds + ML training, scale-to-zero) gpu-inference L4-1-24G (trading inference, scale-to-zero) Build pod limits bumped to 16 vCPU / 64GB (from 6/12GB) to use H100 capacity. Runner now has `gpu` tag — all tests including ml crate run in single job. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
37 lines
1.0 KiB
HCL
37 lines
1.0 KiB
HCL
output "cluster_id" {
|
|
description = "ID of the Kapsule cluster"
|
|
value = scaleway_k8s_cluster.foxhunt.id
|
|
}
|
|
|
|
output "kubeconfig" {
|
|
description = "Kubeconfig file content for the cluster"
|
|
value = scaleway_k8s_cluster.foxhunt.kubeconfig[0].config_file
|
|
sensitive = true
|
|
}
|
|
|
|
output "apiserver_url" {
|
|
description = "URL of the Kubernetes API server"
|
|
value = scaleway_k8s_cluster.foxhunt.apiserver_url
|
|
}
|
|
|
|
output "always_on_pool_id" {
|
|
description = "ID of the always-on node pool"
|
|
value = scaleway_k8s_pool.always_on.id
|
|
}
|
|
|
|
output "gpu_training_pool_id" {
|
|
description = "ID of the GPU training node pool"
|
|
value = var.enable_gpu_training_pool ? scaleway_k8s_pool.gpu_training[0].id : ""
|
|
}
|
|
|
|
output "gpu_inference_pool_id" {
|
|
description = "ID of the GPU inference node pool"
|
|
value = var.enable_gpu_inference_pool ? scaleway_k8s_pool.gpu_inference[0].id : ""
|
|
}
|
|
|
|
output "gitlab_pool_id" {
|
|
description = "ID of the GitLab node pool"
|
|
value = var.enable_gitlab_pool ? scaleway_k8s_pool.gitlab[0].id : ""
|
|
}
|
|
|