Required Compute

AWS Instance Type Recommendations for Model Deployment in Private Cloud

The below compute requirements should be sufficient for deploying OmniAI vis Docker container. Recommended configuration may vary based on total data throughput:

Compute Optimized Instances (For CPU-bound applications):

• Minimum: c5.xlarge, offering 4 vCPUs and 8 GiB of memory, sufficient for basic operations.

• Recommended: c5.2xlarge, providing 8 vCPUs and 16 GiB of memory, suitable for enhanced parallel processing and increased efficiency in handling larger workloads.

Memory Optimized Instances (For applications requiring high memory):

• Minimum: r5.xlarge, equipped with 4 vCPUs and 32 GiB of memory, ideal for applications needing substantial memory but not excessive compute power.

• Recommended: r5.2xlarge equipped with 8 vCPUs and 64 GiB of memory, which provides a robust platform for handling moderate to large datasets efficiently.

Storage:

• EBS-optimized instances with Provisioned IOPS SSD (io1 or io2) volumes are recommended. For most deployments, starting with at least 500GB of storage with 3,000 IOPS is advisable, allowing for high-performance read/write operations and accommodating the storage demands of our Docker images and data.

Networking:

• Choose instances with at least 10 Gigabit connectivity to ensure high throughput and low latency, particularly crucial for maintaining performance and responsiveness in network-intensive operations.