7b9da53603
Create dedicated ci-build node pool (L4-1-24G, €0.75/hr) replacing H100 (€3.50+/hr) for CI builds. H100 reserved for training only. - Add ci-build pool to Terraform (L4-1-24G, scale-to-zero, fr-par-2) - Update GitLab Runner to target ci-build pool with L4-sized limits - Change CUDA_COMPUTE_CAP from 90 (H100) to 89 (L4) in CI - Dockerfile.training keeps CUDA_COMPUTE_CAP=90 for H100 training Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
108 lines
2.4 KiB
HCL
108 lines
2.4 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"
|
|
}
|
|
|
|
variable "enable_ci_build_pool" {
|
|
description = "Create GPU node pool for CI builds (L4)"
|
|
type = bool
|
|
default = false
|
|
}
|
|
|
|
variable "ci_build_type" {
|
|
description = "Instance type for the CI build node pool"
|
|
type = string
|
|
default = "L4-1-24G"
|
|
}
|
|
|
|
variable "ci_build_max_size" {
|
|
description = "Maximum number of nodes in the CI build pool"
|
|
type = number
|
|
default = 1
|
|
}
|
|
|
|
variable "enable_dev_pool" {
|
|
description = "Create CPU node pool for remote development (DevPod)"
|
|
type = bool
|
|
default = false
|
|
}
|
|
|
|
variable "dev_pool_type" {
|
|
description = "Instance type for the dev node pool"
|
|
type = string
|
|
default = "GP1-L"
|
|
}
|
|
|
|
variable "dev_pool_max_size" {
|
|
description = "Maximum number of nodes in the dev pool"
|
|
type = number
|
|
default = 1
|
|
}
|
|
|