• Contact
  • Register
    (If you're a human, don't change the following field)
    Your first name.
    (If you're a human, don't change the following field)
    Your first name.

    Enter your email above, then click "Sign Up" to join the STAC mail list and (optionally) register to access materials on the site. Click for terms.

STAC Research Note: Latency and Throughput Optimization for STAC-ML Markets (Inference)

STAC recently completed a set of experiments that used STAC's naive Python implementation of the STAC-ML Markets Inference benchmark specification using the ONNX runtime as the inference engine. We ran the experiments on two stacks under tests (SUTs).

The SUTs ran identical hardware and software but differed in their configuration:

The experiment's goals were simple: Given a reasonable range of Numbers of Model Instances (NMI) that might be running simultaneously, find the best configuration settings for optimizing Instance Throughput or 99th percentile latency (or both).

The lessons learned in achieving these goals are in this research note.

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