Connect with us

Technology

Myrtle.ai Halves Latency in Financial Machine Learning Inference Benchmark Record with VOLLO

Published

on

CAMBRIDGE, England, April 29, 2026 /PRNewswire/ — myrtle.ai, a recognized leader in accelerating machine learning inference, today announced that a stack featuring its VOLLO® product has recently been audited by STAC®, a leading benchmark authority for the finance industry.[1] The results, unveiled at the STAC Summit in London today, clearly demonstrate the latency benefits of an FPGA-based solution for ML inference in financial trading and related applications.

STAC-ML (Markets) Inference is the technology benchmark standard for solutions that may be used to run inference on real-time market data. Designed by quants and technologists from some of the world’s leading financial firms, STAC-ML Markets (Inference) reports the performance, resource efficiency, and quality of any technology stack capable of performing inference using the provided models.

VOLLO achieved latencies as low as 2 microseconds (99th percentile) while also exhibiting excellent results in throughput and efficiency. Across all three benchmark models, VOLLO inferred in lower latency (99th percentile) than all previously audited systems, halving its previous record. Such low, deterministic latency enables users to make more intelligent decisions using more complex models faster than in the past, giving them a competitive advantage in trading, risk analysis, quotes and many other trading-related activities.

With hundreds of thousands of hours of production trading under its belt, VOLLO is generating alpha for many of the world’s leading trading firms today. Those firms have developed and trained a wide range of models in standard ML tool flows before compiling them into VOLLO and then running them on their choice of FPGA-based hardware platform.

In the system under test, VOLLO ran on the standard form factor FBAP4@VP18-2L0S PCIe accelerator card from Silicom, containing an AMD Versal™ Premium series VP1802 Adaptive SoC and installed in a Supermicro AS -2015CS-TNR server. The AMD Versal Premium Series Adaptive SoC provides PCIe Gen5x8 and more than 3.3M programmable LUTs, making it well suited to low latency inference applications.

“Since VOLLO first exploited the full potential of FPGAs in this STAC benchmark in 2023, we have worked with our customers to further reduce latencies, expand the variety and size of models that VOLLO can run, and grow the range of platforms it can run on,” said Peter Baldwin, CEO of myrtle.ai.  “We’re excited to work with AMD, Silicom and Supermicro on this benchmark, to demonstrate how our combined technologies can enable ultra-low latency AI inference in quant trading.”

“The future of financial markets will be shaped by AI systems that can interpret data and act on it in near real time,” said Girish Malipeddi, director for Data Center FPGA business, AMD. “With AMD Versal™ Premium series adaptive SoCs at the foundation, myrtle.ai’s VOLLO demonstrates how advanced, low-latency inference can help unlock a new generation of intelligent trading infrastructure.”

“Supermicro continues to address a wide range of markets with our AMD systems, which were used for this STAC-ML benchmark,” said Michael McNerney, Senior Vice President Marketing and Network Security, Supermicro. “Our servers address the most challenging workloads in the financial services industry, and together with partners, we are able to deliver top-end performance with very low latencies for machine learning workloads.”

Anders Poulsen, VP Solutions at Silicom Denmark, said: “We’re pleased that myrtle.ai selected Silicom’s Artena accelerator card, based on AMD Versal Premium, for these tests. Built around one of the largest FPGAs in a PCIe form factor, Artena is an ideal platform for VOLLO. Together, VOLLO and our low-latency hardware deliver deterministic, microsecond-level inference for demanding trading workloads.”

ML developers can evaluate today how their models could perform on VOLLO, without the need for any FPGA tools or expertise. For more details go to vollo.myrtle.ai or contact myrtle.ai today at fintech@myrtle.ai.

The full benchmark results are available in the STAC Report (SUT ID MRTL260323) at http://www.STACresearch.com/MRTL260323.

About myrtle.ai

Myrtle.ai is an AI/ML software company that delivers world-class inference accelerators on FPGA-based platforms from all the leading FPGA suppliers. With broad neural network expertise, myrtle.ai has delivered accelerators for applications including fintech, wireless telecoms, LLMs, speech processing, and recommendation.

VOLLO, VOLLO Accelerator and the VOLLO logo are registered trademarks of myrtle.ai.

“STAC” and all STAC names are trademarks or registered trademarks of the Strategic Technology Analysis Center, LLC. AMD, the AMD logo, Versal, and combinations thereof are trademarks of Advanced Micro Devices, Inc. 

[1] www.STACresearch.com/MRTL260323

Photo – https://mma.prnewswire.com/media/2965395/Myrtle_ai.jpg
Logo – https://mma.prnewswire.com/media/2965394/Myrtle_ai_Logo.jpg

 

 

View original content to download multimedia:https://www.prnewswire.com/news-releases/myrtleai-halves-latency-in-financial-machine-learning-inference-benchmark-record-with-vollo-302753225.html

SOURCE Myrtle.ai

Continue Reading
Click to comment

Leave a Reply

Your email address will not be published. Required fields are marked *

Technology

Chef Robotics Physical AI Models Can Now Automate Baked Goods Packing

Published

on

By

SAN FRANCISCO, April 29, 2026 /PRNewswire/ — Chef Robotics, a leader in physical AI for the food industry, today announced that Chef robots can now automate tray assembly for baked goods packing. The application places baked products, such as burger buns, chocolate chip cookies, biscotti, butter cookies, biscuits, fortune cookies, granola bars, rusks, and shortbreads into trays and packaging containers before sealing.

Watch Chef robots in action.

Baked goods packing has historically been difficult to automate for high-mix production. Each item behaves differently on the production line—a granola bar compresses under the wrong grip, while a biscotti or rusk can crack if placed at the wrong angle. Surface textures range from glazed and smooth to crumbly and irregular, and strict presentation requirements leave little room for error. This variability has made it challenging for automation systems to reliably handle baked goods at production speeds, leaving food manufacturers dependent on manual labor and traditional bakery equipment.

To address this, Chef built its baked goods packing application on its existing piece-picking capability, which uses Chef’s AI-powered computer vision and physical AI models trained across diverse real-world production environments. This allows Chef robots to assess each item’s position, shape, and orientation in real time and determine how to pick the items from the pan and place them quickly and precisely without damaging them.

The baked goods packing application supports four distinct placement capabilities.

First, Chef’s vision system detects the angle at which each item sits in the pan and reorients it after picking, placing it on the tray at the exact angle required, regardless of its original position, enabling retail-ready presentation for SKUs that require precise angular placement.

Second, Chef robots can place multiple baked goods into the same packaging container in a single automated pass, completing full tray assembly without manual intervention.

Third, for packaging containers with multiple small compartments, Chef robots can precisely place items into each designated section, including multiple items in the same compartment, using Chef’s AI vision model to detect compartment positions and orientations in real time.

Fourth, Chef’s vision system identifies the exact center of each tray and places every item at a predefined offset from that center, ensuring a uniform, consistent arrangement across every pack regardless of how trays arrive on the conveyor.

For food manufacturers evaluating bakery systems and baked goods packaging automation, the application offers higher throughput, reduced labor dependency, and consistent presentation across shifts. The capability runs on Chef’s existing robotic hardware and software, allowing manufacturers to deploy it without requiring any changes to their production lines.

Chef’s baked goods packing application is available in the U.S., Canada, Germany, and the UK and is included as part of Chef’s robotics-as-a-service (RaaS) pricing model.

About Chef Robotics
Chef is the first company to have commercialized a scalable AI-driven food robotics solution. With over 104 million servings made in production, Chef leverages ChefOS, an AI platform for food manipulation, to offer a Robotics-as-a-Service solution that helps industry-leading food companies increase production volume and meet demand. Headquartered in San Francisco, CA, Chef aims to empower humans to do what humans do best by accelerating the advent of intelligent machines. Visit https://chefrobotics.ai to learn more.

View original content:https://www.prnewswire.com/news-releases/chef-robotics-physical-ai-models-can-now-automate-baked-goods-packing-302756923.html

SOURCE Chef Robotics

Continue Reading

Technology

Chef Robotics Physical AI Models Can Now Automate Baked Goods Packing

Published

on

By

SAN FRANCISCO, April 29, 2026 /PRNewswire/ — Chef Robotics, a leader in physical AI for the food industry, today announced that Chef robots can now automate tray assembly for baked goods packing. The application places baked products, such as burger buns, chocolate chip cookies, biscotti, butter cookies, biscuits, fortune cookies, granola bars, rusks, and shortbreads into trays and packaging containers before sealing.

Watch Chef robots in action.

Baked goods packing has historically been difficult to automate for high-mix production. Each item behaves differently on the production line—a granola bar compresses under the wrong grip, while a biscotti or rusk can crack if placed at the wrong angle. Surface textures range from glazed and smooth to crumbly and irregular, and strict presentation requirements leave little room for error. This variability has made it challenging for automation systems to reliably handle baked goods at production speeds, leaving food manufacturers dependent on manual labor and traditional bakery equipment.

To address this, Chef built its baked goods packing application on its existing piece-picking capability, which uses Chef’s AI-powered computer vision and physical AI models trained across diverse real-world production environments. This allows Chef robots to assess each item’s position, shape, and orientation in real time and determine how to pick the items from the pan and place them quickly and precisely without damaging them.

The baked goods packing application supports four distinct placement capabilities.

First, Chef’s vision system detects the angle at which each item sits in the pan and reorients it after picking, placing it on the tray at the exact angle required, regardless of its original position, enabling retail-ready presentation for SKUs that require precise angular placement.

Second, Chef robots can place multiple baked goods into the same packaging container in a single automated pass, completing full tray assembly without manual intervention.

Third, for packaging containers with multiple small compartments, Chef robots can precisely place items into each designated section, including multiple items in the same compartment, using Chef’s AI vision model to detect compartment positions and orientations in real time.

Fourth, Chef’s vision system identifies the exact center of each tray and places every item at a predefined offset from that center, ensuring a uniform, consistent arrangement across every pack regardless of how trays arrive on the conveyor.

For food manufacturers evaluating bakery systems and baked goods packaging automation, the application offers higher throughput, reduced labor dependency, and consistent presentation across shifts. The capability runs on Chef’s existing robotic hardware and software, allowing manufacturers to deploy it without requiring any changes to their production lines.

Chef’s baked goods packing application is available in the U.S., Canada, Germany, and the UK and is included as part of Chef’s robotics-as-a-service (RaaS) pricing model.

About Chef Robotics
Chef is the first company to have commercialized a scalable AI-driven food robotics solution. With over 104 million servings made in production, Chef leverages ChefOS, an AI platform for food manipulation, to offer a Robotics-as-a-Service solution that helps industry-leading food companies increase production volume and meet demand. Headquartered in San Francisco, CA, Chef aims to empower humans to do what humans do best by accelerating the advent of intelligent machines. Visit https://chefrobotics.ai to learn more.

View original content:https://www.prnewswire.com/news-releases/chef-robotics-physical-ai-models-can-now-automate-baked-goods-packing-302756923.html

SOURCE Chef Robotics

Continue Reading

Technology

Air Products to Expand Industrial Gas Supply for Samsung Electronics’ Next-Generation Semiconductor Fab in South Korea

Published

on

By

New investment underscores the company’s long-term commitment to Korea and its leading role in the global semiconductor industry 

LEHIGH VALLEY, Pa., April 29, 2026 /PRNewswire/ — Air Products (NYSE:APD), a world-leading industrial gases company and serving Samsung globally, today announced it has been selected by Samsung to supply industrial gases for its new advanced semiconductor fab in Pyeongtaek, Gyeonggi Province, South Korea.

Under the agreement, Air Products will build, own and operate multiple state-of-the-art production facilities and a bulk specialty gas supply system to supply nitrogen, oxygen, argon, and hydrogen for Samsung’s new semiconductor fab. The new facilities are expected to come onstream in multiple phases from 2028 through 2030.

Air Products has a long track record of executing multiple phase expansions in Pyeongtaek to support Samsung’s growing manufacturing needs. This latest project represents Air Products’ largest investment to date in the semiconductor industry and will establish Pyeongtaek as the company’s single largest operations site globally supporting the electronics industry. 

“Air Products is honored to be selected once again by Samsung and to have their continued confidence as a trusted partner supporting their strategic growth plans,” said SR Kim, President, Air Products Korea. “This significant investment reinforces Air Products’ role as a leading global supplier to the semiconductor industry and underscores our long-standing commitment to supporting our strategic customers with safety, reliability, efficiency and excellent service.”

Air Products has served the global electronics industry for more than 40 years, supplying industrial gases safely and reliably to many of the world’s leading technology companies. The company has operated in Korea for more than 50 years and has established a strong position in electronics and manufacturing sectors.

About Air Products

Air Products (NYSE: APD) is a world-leading industrial gases company in operation for over 85 years focused on serving energy, environmental, and emerging markets and generating a cleaner future. The Company supplies essential industrial gases, related equipment and applications expertise to customers in dozens of industries, including refining, chemicals, metals, electronics, manufacturing, medical and food. As the leading global supplier of hydrogen, Air Products also develops, engineers, builds, owns and operates some of the world’s largest clean hydrogen projects, supporting the transition to low- and zero-carbon energy in the industrial and heavy-duty transportation sectors. Through its sale of equipment businesses, the Company also provides turbomachinery, membrane systems and cryogenic containers globally.

Air Products had fiscal 2025 sales of $12 billion from operations in approximately 50 countries. For more information, visit airproducts.com or follow us on LinkedInXFacebook or Instagram.

This release contains “forward-looking statements” within the safe harbor provisions of the Private Securities Litigation Reform Act of 1995. These forward-looking statements are based on management’s expectations and assumptions as of the date of this release and are not guarantees of future performance. While forward-looking statements are made in good faith and based on assumptions, expectations and projections that management believes are reasonable based on currently available information, actual performance and financial results may differ materially from projections and estimates expressed in the forward-looking statements because of many factors, including the risk factors described in our Annual Report on Form 10-K for the fiscal year ended September 30, 2025 and other factors disclosed in our filings with the Securities and Exchange Commission. Except as required by law, we disclaim any obligation or undertaking to update or revise any forward-looking statements contained herein to reflect any change in the assumptions, beliefs or expectations or any change in events, conditions or circumstances upon which any such forward-looking statements are based.

View original content to download multimedia:https://www.prnewswire.com/news-releases/air-products-to-expand-industrial-gas-supply-for-samsung-electronics-next-generation-semiconductor-fab-in-south-korea-302757497.html

SOURCE Air Products

Continue Reading

Trending