myrtle.ai Sets STAC Records for Gradient Boosted Tree Inference

Oct 6, 2026
Myrtle.ai says VOLLO recorded latency below 2 microseconds across three gradient boosted tree models and processed up to 50 million inferences per second.

myrtle.ai said in a press release that VOLLO built on its April low latency inference record, setting new STAC-ML Markets benchmark records for gradient boosted tree inference.

In STAC audited tests, VOLLO recorded 99th percentile latency below 2 microseconds across all three models. For the smallest model, it processed 50 million inferences per second with 99th percentile latency of 1.77 microseconds. Myrtle.ai says the results reduced latency by more than 30% and increased throughput by at least five times compared with the previous best results.

The tests used an AMD Alveo V80LL Compute Accelerator in a Blackcore ICON 3132-SM+ server. Developers can also test their own models on VOLLO without using FPGA tools.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Silicon Brief or Daily AI Brief.

Also, consider following us on social media:

AI Chips & Datacenters AI Brief AI Brief (X)
Free newsletter

Silicon Brief

Weekly coverage of AI hardware developments including chips, GPUs, cloud platforms, and data center technology.

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.