Myrtle AI

Enabling Efficient Deployment of AI Services

If you’re scaling up your use or provision of AI, you’re probably concerned about cost, throughput, latency or energy.  You’ll want an optimized solution.  One in which the machine learning model and the platform it runs on work efficiently together.  We optimize machine learning inference workloads for multiple applications in cloud or enterprise data centres and in edge applications.  Our products, expertise and IP ensure optimal use of all available compute resources. achieves 8x throughput advantage with WaveNet

Some of the High Throughput, Latency-bound Inference Workloads We Optimize

Speech Synthesis

Speech Transcription

Machine Translation

Recommendation Systems

Some Examples of the Benefits

Speech Transcription

0 x

More voice channels than a
CPU-only solution

Natural Language Processing

0 x

Lower cost than a CPU-only

Recommendation System

0 x

Up to 10x compute density
per server

Learn More

MAU Accelerator for highest latency-bounded throughput in machine learning inference workloads

SEAL Accelerator for optimizing memory-bound recommendation models in existing infrastructure

Custom Solutions for challenging machine learning applications


One of ten global mlperf benchmark owners

Scroll to Top

This website uses cookies to ensure you get the best experience on our website. By continuing to browse on this website, you accept the use of cookies for the above purposes.