Announcing Novita AI's Partnership With vLLM to Advance AI Inference

Audio By Carbonatix

SAN FRANCISCO--(BUSINESS WIRE)--Apr 10, 2025--

Novita AI, a leading global AI cloud platform, is thrilled to announce a strategic partnership with vLLM, the leading open-source inference engine for large language models (LLMs). This collaboration marks a significant step forward in their shared mission to drive innovation in AI and promote growth within the open-source community.

vLLM is widely recognized for its revolutionary PagedAttention algorithm, which accelerates and optimizes LLM performance during inference. By open-sourcing this technology, vLLM has given developers streamlined, memory-efficient tools they can use across public clouds, model providers, and AI-powered applications—all while reducing operational costs.

“vLLM’s PagedAttention algorithm underscores the transformative power of open-source AI,” said Junyu Huang, Co-Founder & COO at Novita AI. “Through this partnership, we want to empower developers and organizations to leverage these efficiencies and opportunities for more effective AI deployment.”

As part of the collaboration, Novita AI is providing vLLM with high-performance compute resources for testing, benchmarking, research, and development. This support ensures ongoing enhancements to vLLM’s capabilities, optimizing its tools for diverse applications and helping developers deploy large language models in the most efficient ways possible.

Developers using Novita AI’s platform can easily deploy open-source LLMs leveraging vLLM’s advanced inference capabilities. This approach streamlines development, speeds up deployments, and makes scaling AI solutions simpler.

“This collaboration is the start of a longer journey to accelerate AI innovations and equip developers with cutting-edge tools for large-scale impact,” said Junyu Huang.

The partnership reflects both Novita AI’s and vLLM’s commitment to empowering developers and advancing open-source AI. By uniting Novita AI’s robust GPU cloud platform with vLLM’s powerful inference engine, they aim to provide the resources necessary for impactful AI solutions and foster an open-source ecosystem that sparks new ideas and technologies.

“It’s more than just a partnership—it’s a testament to our shared vision for advancing open-source AI and creating fresh possibilities for developers worldwide,” Junyu Huang added.

About Novita AI

Novita AI is an AI cloud platform that helps developers easily deploy AI models through a simple API, backed by affordable and reliable GPU cloud infrastructure. By supporting open-source libraries for LLM inference and serving—like the fast and user-friendly vLLM—Novita AI is driving the future of AI and encouraging innovation across the industry. Learn more about Novita AI at www.novita.ai.

View source version on businesswire.com:https://www.businesswire.com/news/home/20250407357556/en/

CONTACT: Iris Yang

[email protected]

[email protected]

412-509-6163

KEYWORD: UNITED STATES NORTH AMERICA CALIFORNIA

INDUSTRY KEYWORD: SOFTWARE DATA ANALYTICS INTERNET ARTIFICIAL INTELLIGENCE DATA MANAGEMENT PROFESSIONAL SERVICES TECHNOLOGY APPS/APPLICATIONS

SOURCE: Novita AI

Copyright Business Wire 2025.

PUB: 04/10/2025 01:00 PM/DISC: 04/10/2025 01:01 PM

http://www.businesswire.com/news/home/20250407357556/en