Hardware recommendations
What hardware configuration do you recommend for my team size?
Hardware requirements depend on team size, concurrency levels, and model selection. Poolside offers on-premises configurations for smaller teams, mid-sized teams, and large enterprise deployments. Contact Poolside to get a recommended configuration for your intended workload. For an overview of the supported hardware options, see On-premises deployment.Would you recommend 8× RTX 6000 or 2× H200 if that is the hardware available?
Poolside supports an 8× RTX 6000 workstation-rack configuration for on-premises deployments. For BYO H200 systems, Poolside starts at 4× H200 with capacity validation, and the recommended H200 configuration is 8× H200. A 2× H200 configuration is not a documented supported on-premises configuration. If your choice is between a supported 8× RTX 6000 configuration and a 2× H200 configuration, use the 8× RTX 6000 option. If you need H200-specific performance characteristics, contact your Poolside account team to validate the hardware against your intended usage.Multi-tenant isolation
I need to onboard two sovereign customers on the same infrastructure. What do you recommend for isolation?
The current on-premises offerings do not facilitate multi-tenant isolation within a single Poolside deployment. If full tenant isolation is required, deploy separate physical Poolside instances.Shared infrastructure
Can I share a Poolside tower with other applications, or must it be dedicated to Poolside?
Poolside on-premises deployments are full platform deployments that use CPU, memory, storage, and GPU resources on the system. Each on-premises Poolside offering is sized for the intended workload, and Poolside systems should not be shared with other applications.Platform support
We have a GPU as a service platform. Do you support OpenShift?
Yes. Poolside supports Red Hat OpenShift as a deployment path. For more information, see Supported configurations and OpenShift deployment.We have a GPU as a service platform. Do you support Canonical?
Poolside supports self-managed Kubernetes environments such as RKE2 or Charmed Kubernetes. For the current supported deployment paths, see Supported configurations. If you are evaluating a Canonical-managed GPU platform beyond those documented deployment paths, contact your Poolside account team to confirm support requirements and scope.Do you have documentation, reports, or certifications that validate deployment in classified environments?
Poolside supports STIG hardening for Red Hat Enterprise Linux (RHEL) and Ubuntu on on-premises deployments. For deployment guidance, see STIG hardening considerations. For other certifications, documentation, or Software Bill of Materials (SBOM) requests, contact Poolside for further evaluation and assistance.Upgrades and updates
How often do you release updates for both model and software changes?
Poolside releases new on-premises platform software approximately once per quarter. Model families and checkpoints are released on a separate schedule, typically quarterly or when new models become available.How do you update the solution in air-gapped environments?
For air-gapped environments, updates are delivered as complete, self-contained installation bundles. Each bundle supports either a full air-gapped installation or an upgrade from an existing air-gapped deployment. Each Poolside bundle includes all required container images, deployment artifacts, and end-user binaries. Model checkpoints are provided with the initial installation and as new checkpoints become available. For the full procedure, including air-gapped setup, image loading, deployment steps, and validation checks, see Upgrade on-premises.Support
What is the SLA for support?
For details on support eligibility, scope, contact options, and service-level agreement (SLA) response times, see Support Overview and Standard Support.What are the disaster recovery guidelines to support rapid recovery on new infrastructure?
Your organization is responsible for disaster recovery planning for on-premises deployments. Key areas to address include:- Database backups: Regularly back up the PostgreSQL database to enable recovery if the deployment becomes unavailable. For the documented backup workflow, see Backup and restore the database.
- Object storage backups: Back up the S3-compatible object storage (SeaweedFS) that stores models and telemetry data.
- Configuration management: Maintain copies of your deployment configuration and any deployment state files needed to enable redeployment on new hardware.