Nvidia CEO Jensen Huang unveils Dynamo, an open-source inference framework for AI inferencing, at GTC 2025
AI chipmaker Nvidia on Tuesday unveiled Dynamo, an open-source inference framework designed to enhance the deployment of generative AI and reasoning models across large-scale, distributed environments. Announced at the GTC 2025 conference, Dynamo aims to significantly boost inference performance while reducing operational costs for AI applications. The framework supports major AI inference backends, including PyTorch, SGLang, NVIDIA TensorRT-LLM, and vLLM, providing developers and AI researchers with the flexibility to integrate Dynamo into diverse AI workflows. For enterprises seeking accelerated deployment and enterprise-grade support, Nvidia plans to include Dynamo with its NIM microservices, which are part of the NVIDIA AI Enterprise suite.
Discover Related
Forget ChatGPT? China’s DeepSeek is working on smarter, self-improving AI models
Sam Altman Says OpenAI Will Release an ‘Open Weight’ AI Model This Summer
China floods the world with new low-cost AI models after DeepSeek’s success, undercutting OpenAI, Google, and others
DeepSeek rolls out V3 AI model updates in race against OpenAI. What's New?
Tencent upgrades AI model to compete with DeepSeek, Alibaba
Nvidia's Next Big Bet? Robots, Robots, & More Robots!
Nvidia CEO Jensen Huang unveils new Rubin AI chips at GTC 2025
Nvidia looks to further its AI stronghold with new chips and personal supercomputers
Nvidia CEO Jensen Huang unveils new Rubin AI chips at GTC 2025
Nvidia unveils Blackwell Ultra and Vera Rubin, its latest AI superchips
Nvidia CEO Jensen Huang unveils new Rubin AI chips at GTC 2025
Nvidia expected to reveal details of latest AI chip at conference
Nvidia’s next act needs to be even bigger
Chinese AI: Manus ‘agent’ and Alibaba’s new model released in quick succession
OpenAI Launches GPT-4.5 for ChatGPT—It’s Huge and Compute-Intensive
How Nvidia adapted its chips to stay ahead of an AI industry shift
DeepSeek rushes to launch new AI model as China goes all in
How DeepSeek’s AI models gave NVIDIA's H20 chips a major boost in China, sent demand rocketing
How DeepSeek’s AI models gave NVIDIA's H20 chips a major boost in China, sent demand rocketing
Nvidia's H20 chip orders jump as Chinese firms adopt DeepSeek's AI models, sources say
DeepSeek to share some AI model code, doubling down on open source
OpenAI rolls out its Operator AI agent in THESE countries: Check the full list
Nvidia unveils powerful AI system for genetic research
US firms adopt DeepSeek despite scrutiny
OpenAI launches o3-Mini model for free in response to DeepSeek's R1