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>
72 lines
1.6 KiB
HCL
72 lines
1.6 KiB
HCL
variable "region" {
|
|
description = "Scaleway region for the Kapsule cluster"
|
|
type = string
|
|
}
|
|
|
|
variable "cluster_name" {
|
|
description = "Name of the Kubernetes cluster"
|
|
type = string
|
|
default = "foxhunt"
|
|
}
|
|
|
|
variable "k8s_version" {
|
|
description = "Kubernetes version for the Kapsule cluster"
|
|
type = string
|
|
default = "1.34"
|
|
}
|
|
|
|
variable "always_on_type" {
|
|
description = "Instance type for the always-on node pool"
|
|
type = string
|
|
default = "DEV1-M"
|
|
}
|
|
|
|
variable "enable_gpu_training_pool" {
|
|
description = "Create GPU node pool for ML training (H100)"
|
|
type = bool
|
|
default = false
|
|
}
|
|
|
|
variable "gpu_training_type" {
|
|
description = "Instance type for the GPU training node pool"
|
|
type = string
|
|
default = "H100-1-80G"
|
|
}
|
|
|
|
variable "gpu_training_max_size" {
|
|
description = "Maximum number of nodes in the GPU training pool"
|
|
type = number
|
|
default = 1
|
|
}
|
|
|
|
variable "enable_gpu_inference_pool" {
|
|
description = "Create GPU node pool for inference (L4)"
|
|
type = bool
|
|
default = false
|
|
}
|
|
|
|
variable "gpu_inference_type" {
|
|
description = "Instance type for the GPU inference node pool"
|
|
type = string
|
|
default = "L4-1-24G"
|
|
}
|
|
|
|
variable "gpu_inference_max_size" {
|
|
description = "Maximum number of nodes in the GPU inference pool"
|
|
type = number
|
|
default = 1
|
|
}
|
|
|
|
variable "enable_gitlab_pool" {
|
|
description = "Create dedicated node pool for GitLab CE"
|
|
type = bool
|
|
default = false
|
|
}
|
|
|
|
variable "gitlab_type" {
|
|
description = "Instance type for the GitLab node pool"
|
|
type = string
|
|
default = "DEV1-L"
|
|
}
|
|
|