 |
CAMBRIDGE, England, July 29, 2025 /PRNewswire/ -- Myrtle.ai, a recognized leader in accelerating machine learning inference, today released support for its VOLLO® inference accelerator on the AMD Alveo™ V80 compute accelerator card.
VOLLO achieves industry-leading ML inference compute latencies, which can be less than one microsecond, while delivering excellent throughput, power, and rack space efficiencies. This new release enables ML developers with larger models to benefit from running them on a single FPGA for the lowest latency. For example, a 22 million parameter, 3-layer LSTM model can be run with a p99 latency of under 10 microseconds. Even larger models may be sharded and run across multiple FPGAs, still achieving lower latencies than competing solutions.
VOLLO has been in demand across a wide range of applications, including financial trading, wireless telecommunications, cybersecurity, network management, and others, where running ML inference at the lowest possible latency confers advantages in security, safety, profit, efficiency, and cost.
"Demand for VOLLO has come from both sides," remarked Peter Baldwin, CEO of Myrtle.ai. "We have customers who have a fixed latency window, and they're delighted to be able to run larger models at the same latencies that they could only achieve with smaller models before. We also have customers who want the very lowest latency they can achieve for their specific model. Increasing the size of models that can be run on a single FPGA has really helped both."
"We're delighted that VOLLO is now supported on the production-ready AMD Alveo V80 compute accelerator for memory-intensive workloads," said Girish Malipeddi, director for Data Center FPGA business, AMD. "AMD customers can now run ML inference at very low latency using VOLLO, while those wishing to purchase a compute accelerator to run VOLLO have the option to choose the Alveo V80, with the highest model capacity of any single FPGA yet supported by VOLLO."
The Alveo V80 card is based on the AMD Versal™ Adaptive SoC with 2.6M LUT logic density, 32GB of HBM, and an additional 32GB of DDR4 and 800G network interface. It features FPGA fabric to adapt the hardware to the application, coupled with HBM2e for large data sets and memory-intensive compute.
Interested parties may now download the ML-oriented VOLLO compiler from vollo.myrtle.ai today and discover what latencies can be achieved with their models on the AMD Alveo V80 compute accelerator card.
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 neural network expertise across the complete spectrum of ML networks, Myrtle has delivered accelerators for FinTech, Speech Processing, and Recommendation.
AMD, the AMD logo, Alveo, Versal, and combinations thereof are trademarks of Advanced Micro Devices, Inc.
CAMBRIDGE, England, July 29, 2025 /PRNewswire/ -- Myrtle.ai, a recognized leader in accelerating machine learning inference, today released support for its VOLLO® inference accelerator on the AMD Alveo™ V80 compute accelerator card.
VOLLO achieves industry-leading ML inference compute latencies, which can be less than one microsecond, while delivering excellent throughput, power, and rack space efficiencies. This new release enables ML developers with larger models to benefit from running them on a single FPGA for the lowest latency. For example, a 22 million parameter, 3-layer LSTM model can be run with a p99 latency of under 10 microseconds. Even larger models may be sharded and run across multiple FPGAs, still achieving lower latencies than competing solutions.
VOLLO has been in demand across a wide range of applications, including financial trading, wireless telecommunications, cybersecurity, network management, and others, where running ML inference at the lowest possible latency confers advantages in security, safety, profit, efficiency, and cost.
"Demand for VOLLO has come from both sides," remarked Peter Baldwin, CEO of Myrtle.ai. "We have customers who have a fixed latency window, and they're delighted to be able to run larger models at the same latencies that they could only achieve with smaller models before. We also have customers who want the very lowest latency they can achieve for their specific model. Increasing the size of models that can be run on a single FPGA has really helped both."
"We're delighted that VOLLO is now supported on the production-ready AMD Alveo V80 compute accelerator for memory-intensive workloads," said Girish Malipeddi, director for Data Center FPGA business, AMD. "AMD customers can now run ML inference at very low latency using VOLLO, while those wishing to purchase a compute accelerator to run VOLLO have the option to choose the Alveo V80, with the highest model capacity of any single FPGA yet supported by VOLLO."
The Alveo V80 card is based on the AMD Versal™ Adaptive SoC with 2.6M LUT logic density, 32GB of HBM, and an additional 32GB of DDR4 and 800G network interface. It features FPGA fabric to adapt the hardware to the application, coupled with HBM2e for large data sets and memory-intensive compute.
Interested parties may now download the ML-oriented VOLLO compiler from vollo.myrtle.ai today and discover what latencies can be achieved with their models on the AMD Alveo V80 compute accelerator card.
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 neural network expertise across the complete spectrum of ML networks, Myrtle has delivered accelerators for FinTech, Speech Processing, and Recommendation.
AMD, the AMD logo, Alveo, Versal, and combinations thereof are trademarks of Advanced Micro Devices, Inc.
** The press release content is from PR Newswire. Bastille Post is not involved in its creation. **
Myrtle.ai Enables Microsecond ML Inference Latencies for Larger Models on AMD Alveo V80 Compute Accelerator Card
The Initiative Aims to Address the Pain Points of Family Filmmaking
BEIJING, Dec. 13, 2025 /PRNewswire/ -- On December 6th, the 3rd FamilyLens International Film Festival opened in Beijing. SmallRig, a global specialized provider of imaging solutions, collaborating with FamilyLens, is empowering family filmmaking through various initiatives, including the Family Filmmaking Co-Creation Initiative, a dedicated family filmmaking kit, and a social impact screening program.
Deepening the "Co-Creation Initiatives"
The Co-Creation Initiatives are a series of global creative initiatives open to filmmakers and image creators worldwide. Through deep collaboration across multiple dimensions — including product co-creation, discovery and promotion, and content co-creation — SmallRig aims to expand the boundaries of mobile filmmaking and bring the spirit of Free Your Dream to life with creators everywhere.
Following the launch of the Mobile Filmmaking Co-Creation Initiative at the 14th International Smartphone Film Festival, SmallRig announced the launch of the Family Filmmaking Co-Creation Initiative on December 6th at the 3rd FamilyLens International Film Festival. The initiative invites global creators and every family to participate, focusing on three core directions: product co-creation, work promotion, and content co-creation, to explore the possibilities of family filmmaking for everyone.
Mr. Zhou Yang, Founder and CEO of SmallRig, shared the inspiration for the initiative: "The initiative is rooted in the immense universality and profound emotional depth inherent in family narratives, which serve as a common emotional bond connecting global audiences. We firmly believe that in this era, where everyone can be a content creator, every family can and should film their own story. The instinct to create is deeply embedded in the human spirit, and every home is the origin of countless narratives."
Gu Xue, Founder and Director of the FamilyLens International Film Festival, stated: "We hope that people and practitioners around the world who care about family movies can find suitable solutions and gain insights from the Co-Creation Initiatives. We look forward to more and more people exploring the field of 'Home' together through this initiative."
To address the pain points of family filmmaking, SmallRig officially released the SmallRig Family Filmmaking Kit at the opening ceremony. The kit includes a high-quality microphone, fill light, and a portable tripod, specifically designed to achieve "professional function democratization" and "complex feature simplification." During the FamilyLens Workshop, attendees experienced the convenience of the equipment firsthand. Many expressed that the kit truly solves many problems, enabling ordinary families to complete necessary filming without specialized photography knowledge.
Social Impact Screening Program
The 3rd FamilyLens International Film Festival is open to the public from December 6th to 14th. The festival opened with the screening of well-received documentary: K-Family Affairs. In addition to the competition section, the festival features several distinctive sections, including the Reframing Home Movies— An Italian Retrospective, Youth Film Program, Filmmaker in Focus, and the Social Impact Program. Four major awards, such as the Real-Life Portrait Award and the Artistic Exploration Award, will also be presented.
As a key component of the Co-Creation Initiatives, the SmallRig Image Development Fund partnered with the FamilyLens International Film Festival to curate the "Social Impact Screening Program." This unit focuses on elevating awareness of critical issues within the family unit, advocating for a new reflection: "Starting with Seeing, Concluding with Understanding."
Arum Nam, Director of K-Family Affairs, stated:
"Starting with the stories of your family, your friends, and yourself, I believe this personal narrative can connect directly to the bigger society."
SmallRig believes that truly meaningful social impact storytelling stems from awareness in proximity—achieved by using the lens to penetrate the daily surface and enabling a deep, empathetic "Seeing with Empathy."
The four featured works in this unit are:
- People of the Ascent
- Granny's Lost and Found
- Ruixi at Fourteen
- No Country For My Maternal Grandma
These films highlight four family issues that require "seeing": the yearning of left-behind children, the mental isolation of Alzheimer's patients, the elderly searching for subjectivity in their drifting lives, and the emotional volatility and struggle of Bipolar Disorder.
Strategic Outlook and Future Expansion
SmallRig will continue to support the Family Filmmaking Co-Creation Initiative's deep development through promotional campaigns and practical workshops focused on family movie scenarios.
The overall goal of SmallRig's Global Co-creation Initiative is to continuously explore and meet the growing, diverse needs of global creators across different vertical domains. SmallRig is committed to persistently expanding the co-creation model into more imaging sectors, collaborating with industry partners to push the boundaries of imaging and grant global creators broader creative freedom.
About SmallRig
Founded in 2013, SmallRig is an innovation-driven global company that designs and manufactures comprehensive support solutions and accessories for all content creation needs. Trusted by over four million creators globally, SmallRig pioneered the User Co-creation Design (UCD) philosophy and the DreamRig Program.
For more information, visit: www.smallrig.com.
** The press release content is from PR Newswire. Bastille Post is not involved in its creation. **
SmallRig and FamilyLens Launch Global Family Filmmaking Initiative at 3rd FamilyLens International Film Festival
SmallRig and FamilyLens Launch Global Family Filmmaking Initiative at 3rd FamilyLens International Film Festival
SmallRig and FamilyLens Launch Global Family Filmmaking Initiative at 3rd FamilyLens International Film Festival
