A machine learning inference accelerator for the finance industry

Designed for fintech

VOLLO™ is designed to achieve the best latency, throughput, quality and energy- and space-efficiency metrics for the STAC-ML Markets (Inference) benchmarks1.

Very low latency

VOLLO achieves extremely low latencies for the LSTM-based neural network models defined in the STAC–ML benchmarks2.

Simple to install

VOLLO runs on the IA-840f, an industry-standard FHFL PCIe accelerator card from Molex, powered by an Intel® Agilex™ FPGA.

High accuracy

High accuracy is achieved through the use of floating point format in all operations. Models can be trained in FP32 and run on VOLLO without the need for retraining or accuracy compromises.

High throughput and power-efficiency

Designed to be installed in a server co-located in a stock exchange, VOLLO employs hardware acceleration on an FPGA. This results in very high throughput and low energy consumption per card, significantly reducing the costs incurred in running co-located servers.

Simple to program

Models can be trained in PyTorch or TensorFlow before being exported in ONNX format into the VOLLO tool suite, making it simple to program from your existing ML development environment.

Flexible for future-proofing

The flexibility of FPGA technology ensures that not only can VOLLO be software-configured with users’ LSTM model configurations, but significant architectural innovations can also be adopted quickly with optimal compute structures3.

Learn more about VOLLO, and what it can do for your business

Contact Us

1 STAC® is the Securities Technology Analysis Center

2 Performance pending audit by STAC

3 Myrtle.ai can provide optimized FPGA bitstreams for new and emerging models based on an extensive IP library for AI inference. 

TensorFlow, the TensorFlow logo and any related marks are trademarks of Google Inc.
PyTorch, the PyTorch logo and any related marks are trademarks of The Linux Foundation.