Cluster blueprint catalog

A cluster blueprint is a YAML file that defines a reusable configuration and describes the specific environment that you want to deploy using Cluster Toolkit. A cluster blueprint implements and documents a specific opinionated solution. For more information about cluster blueprints, see Cluster blueprint.

To search the catalog, you can filter by a combination of your required scheduler, storage, machine types, and base operating system. For each cluster blueprint, featured applications and Google Cloud resources that can be leveraged by using the blueprint are also highlighted.

Cluster blueprintSchedulerStorageMachine typesBase operating systemFeatured software and compute resourcesCollection
a4-highgpu-8gSlurmFilestore, Cloud Storage, Google Cloud Managed Lustre (requires allowlist inclusion)A4ubuntu-accelerator-2204-amd64-with-nvidia-570
  • NVIDIA ConnectX-7
  • Google Virtual NIC (gVNIC)
  • GPUs
  • Virtual Private Cloud
Core
gke-a3-ultragpuGKEFilestore, Cloud StorageA3 UltraContainer-Optimized OS
  • NVIDIA ConnectX-7
  • Google Virtual NIC (gVNIC)
  • GPUs
  • Virtual Private Cloud
Core
gke-a3-highgpuGKENoneA3 HighContainer-Optimized OS
  • Jobset
  • Kueue
Core
gke-a3-megagpuGKENoneA3 MegaContainer-Optimized OS
  • Jobset
  • Kueue
Core
gke-managed-hyperdiskGKEFilestore, Cloud StorageC3Container-Optimized OSCore
gke-managed-parallelstoreGKEParallelstoreN2Container-Optimized OSCore
gke-a4GKEA4Container-Optimized OS
  • Jobset
  • Kueue
Core
a3-ultragpu-8gSlurmFilestore, Cloud Storage, Google Cloud Managed Lustre (requires allowlist inclusion)A3 Ultraubuntu-accelerator-2204-amd64-with-nvidia-570
  • NVIDIA ConnectX-7
  • Google Virtual NIC (gVNIC)
  • GPUs
  • Virtual Private Cloud
Core
a3-highgpu-8gSlurmFilestore, Cloud StorageA3 Highubuntu-2004-lts*
  • Google Virtual NIC (gVNIC)
  • GPUs
  • Virtual Private Cloud
Core
a3-megagpu-8gSlurmFilestore, Cloud StorageA3 Megadebian-12*
  • Google Virtual NIC (gVNIC)
  • GPUs
  • Virtual Private Cloud
Core
hpc-slurmSlurmFilestoreN2, C2, H3hpc-rocky-linux-8*Core
hpc-enterprise-slurmSlurmFilestore, Filestore High Scale, DDN-EXAScaler LustreN2, C2, C3, A2, H3hpc-rocky-linux-8*
  • Google Virtual NIC (gVNIC)
  • GPUs
  • Performance persistent disks (pd-ssd)
  • Tier_1 networking
Core
hpc-slurm6-tpu-maxtextSlurmNoneTPUv4, N2, C2slurm-gcp-6-4-tf-2.14.0*
  • TPUs
  • Maxtext
Community, Experimental
ml-slurmSlurmFilestore, Cloud StorageN2, A2, G2debian-11*
  • GPUs
  • NCCL
  • PyTorch
  • TensorFlow
Core
serverless-batchBatchFilestoreN2rocky-linux-8-optimized-gcpCore
serverless-batch-mpiBatchFilestoreC2hpc-rocky-linux-8
  • Spack
  • Weather Research and Forecasting (WRF)
Core
tutorial-starccmNoneFilestoreC2hpc-centos-7
  • Star CCM+
Community, Experimental
tutorial-fluentNoneFilestoreC2hpc-rocky-linux-8
  • Ansys Fluent
Community, Experimental
image-builderSlurmFilestoreC2, N2hpc-rocky-linux-8*
  • Packer
Core
hpc-build-slurm-imageSlurmNoneN2Dhpc-rocky-linux-8*
  • Packer
  • Building Slurm
Community
hpc-amd-slurmSlurmFilestoreC2Dhpc-rocky-linux-8*
  • AMD
  • AMD Optimizing C/C++ and Fortran Compilers (AOCC)
  • OpenFoam
  • Spack
Community
hpc-slurm-local-ssdSlurmFilestoreN1hpc-rocky-linux-8*
  • Local SSDs
Community, Experimental
hpc-slurm-ubuntu2004SlurmFilestoreN2, C2ubuntu-2004-ltsCommunity
hpc-slurm-gromacsSlurmFilestoreC2hpc-rocky-linux-8*
  • GROMACS
  • Spack
Community, Experimental
hpc-slurm-hclsSlurmCloud Storage, FilestoreA2, C2hpc-rocky-linux-8*
  • GPUs
  • GROMACS on GPUs
  • Spack
  • VDI with VMD
Community
htc-htcondorHTCondorNoneC2hpc-rocky-linux-8Community, Experimental
ml-gkeGKENoneN2, A2Container-Optimized OS
  • GPUs
Community, Experimental
hpc-gkeGKENoneN2, C2Container-Optimized OSCommunity, Experimental
storage-gkeGKEFilestore, ephemeral storageN2DContainer-Optimized OS
  • Local SSDs
  • CSI Drivers
  • Persistent Volumes
Community, Experimental
client-google-cloud-storageNoneCloud StorageE2hpc-rocky-linux-8Community, Experimental
htc-slurmSlurmFilestore, Filestore High Scale, DDN EXAScaler LustreN2, C2hpc-rocky-linux-8*
  • Configured for high-throughput applications
Community, Experimental
hpc-slurm-sharedvpcSlurmFilestoreN2, C2hpc-rocky-linux-8*
  • Shared VPC configuration
Community

*This OS image is an optimized Schedmd's Slurm image that is based on the specified operating system.

This OS image has DAOS drivers pre-installed and needs to be built following instructions in the DAOS project.

What's next