STAC-ML Markets (Inference) Naive Implementation with ONNX on a 60-vCPU Sole-Tenant Cloud Node with 240 GiB Memory - Throughput-Optimized Configuration

Audited

STAC-ML Markets (Inference)

Throughput-optimized

  • STAC-ML Markets (Inference) Naive Implementation, Compatibility Rev A
  • Inference Engine
    • Python 3.8.10
    • ONNX runtime 1.11.0
    • NumPy 1.22.3
  • Ubuntu Linux 20.04.4 LTS
    • Based on a standard image provided by Google Cloud
    • No OS tuning
  • A Google Cloud c2-node-60-240 sole-tenant node
    • 60 x Intel® Xeon® Family 6 Model 85 Stepping 7 (Cascade Lake) vCPUs at 3.1GHz
    • 240 GiB of memory
    • 150 GB balanced persistent disk

Please log in to see file attachments. If you are not registered, you may register for no charge.

The STAC-ML Working Group develops benchmark standards for key machine learning (ML) workloads in finance. These benchmarks enable customers, vendors, and STAC to make apples-to-apples comparisons of techniques and technologies.

Read more