Vault Report: STAC-ML Markets (Inference) Tacana on GroqNode with a GroqCard Accelerator

Groq provides unaudited STAC-ML results on sliding windows.

28 November 2023

Groq recently submitted unaudited results for STAC-ML Markets (Inference) Tacana suite to the STAC Vault for a stack consisting of a GroqNode™ with a single GroqCard™ accelerator.

STAC-ML Markets (Inference) is the technology benchmark standard for solutions that may be used to run inference on realtime market data. Designed by quants and technologists from some of the world's leading financial firms, the benchmark reports the performance, resource efficiency, and quality of any technology stack capable of performing inference using the provided models. In this project, Groq ran the sliding-window benchmark suite (code named Tacana).

The stack consisted of the STAC-ML Pack for GroqWare™ Tacana (Rev A) using the GroqWare SDK 0.9.2, C++20 (g++ 11.4.0), and Python 3.8.15 on a GroqNode™ server with a GroqCard™ Accelerator.

The report and detailed configuration information are now available to eligible subscribers. If your firm does not have access to these materials, please take a minute to learn about subscription options.