NVIDIA announces the creation of a full-blooded DeepSeek inference world record
NVIDIA announced the world record-setting DeepSeek-R1 inference performance at NVIDIA GTC 2025. A single NVIDIA DGX system equipped with eight NVIDIA Blackwell GPUs can achieve over 250 tokens per user per second, or a maximum throughput of over 30,000 tokens per second, on the fully powered 671 billion parameter DeepSeek-R1 model. (AI Cambrian)
Source: Wallstreetcn The copyright of this article belongs to the original author/organization.
The views expressed herein are solely those of the author and do not reflect the stance of the platform. The content is intended for investment reference purposes only and shall not be considered as investment advice. Please contact us if you have any questions or suggestions regarding the content services provided by the platform.
Post your comment
No Comments