Our Vision
Rapid advances in the development of ever-more-complex machine learning algorithms and an explosion in the use of machine learning to introduce AI into all walks of life is massively increasing demand for compute capacity and the energy required to power it. The need for low latency in real-time applications is exacerbating that trend. Growth is unsustainable using traditional software-only solutions.
Our vision is to produce machine learning inference solutions which meet these exacting demands using minimum compute capacity and minimum energy, thus advancing the vast potential of machine learning to enhance our lives without costing the planet.
News
Myrtle.ai is proud to be a founding member of MLCommons
New open engineering consortium established to accelerate innovation in ML
Myrtle.ai delivers up to 16x throughput advantage for ASR using WaveNet
Achieves high fidelity speech synthesis at lower cost using Intel® Stratix® 10 NX FPGA
Myrtle.ai Solves Core Recommendation Model Challenge with SEAL
Enables large cost savings with a straightforward scale up of existing infrastructure
Myrtle.ai launches new domain-specific, sparsity-exploiting inference accelerator at Xilinx Developer Forum 12 November 2019
Delivers very high throughput within tight latency bounds
Myrtle.ai releases optimized speech inference solution for the Intel® FPGA PAC D5005 platform
Reduces costs and removes growth constraints for businesses offering speech services
Myrtle.ai selected to provide artificial intelligence benchmark code for internationally recognised competition
MLPerf selects myrtle.ai to provide benchmark code for Speech To Text
Key Staff
Contact Us
If you’re interested in the efficient deployment of AI-based services using inferencing on DNNs, we’re interested in hearing from you.
Visit Us
3rd Floor, 50 St Andrew’s St, Cambridge CB2 3AH, UK
TRUSTED BY
