Business Wire

Gcore Unveils Inference at the Edge – Bringing AI Applications Closer to End Users for Seamless Real-Time Performance

6.6.2024 11:30:00 EEST | Business Wire | Press release

Share

Gcore, the global edge AI, cloud, network, and security solutions provider, today announced the launch of Gcore Inference at the Edge, a breakthrough solution that provides ultra-low latency experiences for AI applications. This innovative solution enables the distributed deployment of pre-trained machine learning (ML) models to edge inference nodes, ensuring seamless, real-time inference.

This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20240606719181/en/

To view this piece of content from mms.businesswire.com, please give your consent at the top of this page.

Gcore Inference at the Edge empowers businesses across diverse industries with cost-effective, scalable, and secure AI model deployment (Graphic: Gcore)

Gcore Inference at the Edge empowers businesses across diverse industries—including automotive, manufacturing, retail, and technology—with cost-effective, scalable, and secure AI model deployment. Use cases such as generative AI, object recognition, real-time behavioural analysis, virtual assistants, and production monitoring can now be rapidly realised on a global scale.

Gcore Inference at the Edge runs on Gcore's extensive global network of 180+ edge nodes, all interconnected by Gcore's sophisticated low-latency smart routing technology. Each high-performance node sits at the edge of the Gcore network, strategically placing servers close to end users. Inference at the Edge runs on NVIDIA L40S GPUs, the market-leading chip designed specifically for AI inference. When a user sends a request, an edge node determines the route to the nearest available inference region with the lowest latency, achieving a typical response time of under 30 ms.

The new solution supports a wide range of fundamental ML and custom models. Available open-source foundation models in the Gcore ML Model Hub include LLaMA Pro 8B, Mistral 7B, and Stable-Diffusion XL. Models can be selected and trained agnostically to suit any use case, before distributing them globally to Gcore Inference at the Edge nodes. This addresses a significant challenge faced by development teams where AI models are typically run on the same servers they were trained on, resulting in poor performance.

Benefits of Gcore Inference at the Edge include:

  • Cost-effective deployment: A flexible pricing structure ensures customers only pay for the resources they use.
  • Inbuilt DDoS protection: ML endpoints are automatically protected from DDoS attacks through Gcore’s infrastructure.
  • Outstanding data privacy and security: The solution features built-in compliance with GDPR, PCI DSS, and ISO/IEC 27001 standards.
  • Model autoscaling: Autoscaling is available to handle load spikes, so a model is always ready to support peak demand and unexpected surges.
  • Unlimited object storage: Scalable S3-compatible cloud storage that grows with evolving model needs.

Andre Reitenbach, CEO at Gcore comments: “Gcore Inference at the Edge empowers customers to focus on getting their machine learning models trained, rather than worrying about the costs, skills, and infrastructure required to deploy AI applications globally. At Gcore, we believe the edge is where the best performance and end-user experiences are achieved, and that is why we are continuously innovating to ensure every customer receives unparalleled scale and performance. Gcore Inference at the Edge delivers all the power with none of the headache, providing a modern, effective, and efficient AI inference experience.”

Learn more at https://gcore.com/inference-at-the-edge

About Gcore
Gcore is the global edge AI, cloud, network, and security solutions provider. Gcore provides its solutions to global leaders in numerous industries. The company manages its own global IT infrastructure across six continents, with one of the best network performances in Europe, Africa, and LATAM, due to the average response time of 30 ms worldwide. Gcore’s network consists of 180+ points of presence around the world in reliable Tier IV and Tier III data centres, with a total capacity exceeding 200 Tbps.

To view this piece of content from cts.businesswire.com, please give your consent at the top of this page.

Contact information

Gcore press contact
pr@gcore.com

About Business Wire

For more than 50 years, Business Wire has been the global leader in press release distribution and regulatory disclosure.

Subscribe to releases from Business Wire

Subscribe to all the latest releases from Business Wire by registering your e-mail address below. You can unsubscribe at any time.

Latest releases from Business Wire

Access Advance Welcomes Meta Platforms, Inc. and Alibaba Group to the Video Distribution Patent Pool3.7.2026 02:00:00 EEST | Press release

Access Advance LLC today announced that Meta Platforms, Inc., one of the world's largest distributors of video content across its Facebook, Instagram, Threads, and WhatsApp services, has joined the Video Distribution Patent Pool (VDP Pool) as a Licensee. Meta also joined both the HEVC Advance and VVC Advance pools as a Licensee. Alibaba Group, whose video infrastructure spans a wide range of video-based services across e-commerce, entertainment, and digital media platforms, was also announced as a VDP Pool Licensee this week. Meta and Alibaba joining the VDP Pool further reinforces the program’s market leading position in resolving the licensing issues around the use of modern video codecs, including VP9, AV1, HEVC and VVC, across all the diverse business models of internet video streaming. "A significant U.S.-based company like Meta joining as a Licensee is a milestone moment for the content distribution business and the VDP Pool," said Peter Moller, CEO of Access Advance. "Meta reach

Kioxia Commences Sample Shipments of 10th-Generation BiCS FLASH™ Devices Delivering High Performance, High Capacity and Low Power Consumption3.7.2026 02:00:00 EEST | Press release

Kioxia Corporation, a world leader in memory solutions, today announced that it has commenced sample shipments of 1Tb (terabit) Triple-Level-Cell (TLC) memory devices utilizing its 10th-generation BiCS FLASH™ 3D flash memory technology.1 These will be primarily integrated into the company’s enterprise and data center SSDs, strengthening Kioxia’s lineup to meet the growing demand for AI storage, which requires higher performance, higher capacity, and lower power consumption. These new products will be manufactured using state-of-the-art equipment at Kioxia’s Kitakami Plant Fab2 facility in Iwate Prefecture, Japan. By leveraging innovative CMOS directly Bonded to Array (CBA) technology2 and On-Pitch Select Gate Drain (OPS) technology,3 both adopted since the 8th-generation BiCS FLASH™, the 10th-generation technology achieves a NAND interface speed of 4.8 Gb/s,4 a 33% improvement over the 8th generation. Bit density has increased by 59% by stacking 332 layers and improving lateral density

Bending Spoons S.p.A. announces closing of initial public offering2.7.2026 21:35:00 EEST | Press release

Bending Spoons S.p.A. (“Bending Spoons”), a leading technology company, today announces the closing of its initial public offering of an aggregate of 57,971,015 of its ordinary shares, at an initial public offering price of $29.00 per share. The offering consisted of 34,398,640 shares sold by Bending Spoons and 23,572,375 shares sold by certain selling shareholders (the “Selling Shareholders”). The gross proceeds from the offering to Bending Spoons, before deducting underwriting discounts and commissions and other offering expenses, was approximately $953,917,285.50. Bending Spoons did not receive any proceeds from the sale of shares by the Selling Shareholders. Bending Spoons’ ordinary shares began trading on the Nasdaq Global Select Market on July 1, 2026 under the ticker symbol “BSP”. Goldman Sachs International, J.P. Morgan, and Allen & Company LLC are acting as joint lead book-running managers for the offering. Wells Fargo Securities, BofA Securities, Jefferies, Evercore ISI, BNP

Strategic Partnership Between Record Asset Management and Admicasa2.7.2026 20:00:00 EEST | Press release

RAM Swiss Holding AG is a subsidiary of LSE-listed Record Financial Group (Record) and part of the Record Asset Management (RAM) group of companies. The partnership is a milestone in the growth of Admicasa and marks an important step in the continued expansion of Record’s private markets platform. Subject to regulatory approval, the agreement, signed on 1st July 2026, provides RAM Swiss Holding AG with a 50% participation in the Admicasa Fondsleitung AG, part of Admicasa, and establishes a long-term partnership to develop investment opportunities in the Swiss and Global real estate market with a plan to expand into other asset classes in the medium term. RAM is the European asset management arm of Record, the LSE-listed specialist investment group managing USD 115 billion of assets on behalf of institutional clients worldwide. Record's client base comprises pension funds, foundations, sovereign institutions and other asset managers, with whom it has built long-standing relationships th

IQM Quantum Computers Becomes First European Quantum Computing Company Listed on a Major U.S. Exchange2.7.2026 17:47:00 EEST | Press release

IQM Quantum Computers (Nasdaq: IQMX) (“IQM”, “IQM Quantum Computers” or the “Company”), a global leader in full-stack superconducting quantum computers, today became a publicly traded company following the completion of its business combination with Real Asset Acquisition Corp. (“RAAQ”). This press release features multimedia. View the full release here: https://www.businesswire.com/news/home/20260702960460/en/ IQM Quantum Computers Becomes First European Quantum Computing Company Listed on a Major U.S. Exchange The company’s American Depositary Shares begin trading today on the Nasdaq Global Select Market under the ticker symbol “IQMX”. The listing marks a major milestone for IQM establishing the company as the first European quantum computing company listed on a major U.S. stock exchange. Due to the proceeds of the transaction, IQM maintains a strong pro forma cash position of EUR 337 million. IQM enters the public markets with strong commercial momentum and a rapidly expanding globa

In our pressroom you can read all our latest releases, find our press contacts, images, documents and other relevant information about us.

Visit our pressroom
World GlobeA line styled icon from Orion Icon Library.HiddenA line styled icon from Orion Icon Library.Eye