– Jointly Enabling High-Performance, Production-Scale AI Inference for Global Companies

SAN FRANCISCO: #inference--FriendliAI, The Frontier AI Inference Cloud, is collaborating with Samsung SDS, a leading GPU infrastructure-as-a-service (IaaS) provider in South Korea, to deliver frontier model AI inference services to global startups and enterprises. The initiative brings together FriendliAI's high-performance inference stack and Samsung Cloud Platform (SCP)'s scalable NVIDIA B300 GPU infrastructure.

FriendliAI is known for building an AI inference platform that delivers unmatched speed, cost efficiency, and reliability. By integrating FriendliAI’s platform with Samsung SCP’s B300 GPU infrastructure, the two companies will enable customers to run the latest frontier open-weight models - including GLM-5.1, MiniMax M2.5, NVIDIA Nemotron 3 Super, and DeepSeek v3.2 at maximum performance with production-grade reliability and competitive token pricing.

Bringing Frontier Open-Weight Model AI Inference to Global Companies

The partnership is designed to provide organizations worldwide with a seamless and scalable experience when deploying frontier AI models. Customers will be able to access FriendliAI’s inference platform powered by Samsung SCP’s NVIDIA B300 GPU IaaS, combining state-of-the-art inference optimization with high-performance GPU infrastructure. Key benefits include:

Day-0 Support for Frontier Open-Weight Models: Immediate support for models such as GLM-5.1, MiniMax M2.5, NVIDIA Nemotron 3 Super, and DeepSeek v3.2 enables companies to stay at the forefront of AI innovation without building and maintaining custom inference stacks.

High-Performance Inference: FriendliAI’s optimized platform is built on its in-house inference engine featuring custom kernels, advanced quantization techniques, intelligent caching, and adaptive speculative decoding.

Cost-Effective Scalability: The partnership enables high-speed inference with low operational cost and maximum scalability. Friendli Serverless Endpoints provide a flexible, token-based pricing model and pay only for the tokens they process.

Global Reach and Reliability: FriendliAI’s inference infrastructure, integrated with Samsung SCP’s B300 IaaS platform, provides a global footprint with high-availability guarantees, ensuring low-latency and stable service delivery for customers worldwide.

“FriendliAI is thrilled to partner with Samsung SCP to empower AI inference for companies around the world,” said Byung-Gon Chun, Founder and CEO of FriendliAI. “Our inference optimization technology, built for unmatched speed and cost efficiency, perfectly complements Samsung SCP’s cutting-edge NVIDIA B300 GPU cloud infrastructure. This collaboration allows us to deliver the latest frontier open-weight models at full performance, helping customers unlock new business opportunities with agentic AI.”

EUNYOUNG KIM, Executive Vice President at Samsung SDS, added, “Our mission at Samsung SCP is to provide flexible and high-performance GPU infrastructure for the AI era. Partnering with FriendliAI enables us to bring state-of-the-art AI inference capabilities to global customers. FriendliAI’s platform ensures that our NVIDIA B300 GPUs are fully utilized, offering clients the optimal combination of performance, cost efficiency, and reliability for frontier AI workloads.”

About FriendliAI

FriendliAI is The Frontier AI Inference Cloud. Built by the researchers who invented continuous batching, FriendliAI’s highly optimized inference engine efficiently runs state-of-the-art open-weight and custom models at production scale with 99.99% reliability. By maximizing GPU utilization, FriendliAI delivers speeds up to 3x faster than vLLM and 50% to 90% cost savings relative to closed model APIs, empowering engineers to deploy frontier AI with uncompromising speed and model ownership. Learn more at https://friendli.ai

About Samsung Cloud Platform (SCP)

Samsung Cloud Platform is a leading GPU infrastructure-as-a-service (IaaS) provider operating clusters based on NVIDIA B300 GPUs. Samsung SCP offers scalable, high-availability GPU resources designed to accelerate compute-intensive workloads such as AI inference and training. Its mission is to empower organizations with flexible, cost-effective infrastructure that keeps pace with the rapid evolution of artificial intelligence. Learn more at https://cloud.samsungsds.com/

Fonte: Business Wire