DeepSeek open-sources DeepInfer to cut the cost of running AI models
Photo: Crypto Briefing
The Hangzhou lab is giving away the inference engine behind its latest model, betting that cheaper deployment wins more developers DeepSeek is giving away one of the tools it uses to run its own AI. On October 20, 2026, the Hangzhou-based lab open-sourced DeepInfer, the inference framework it built to serve production models at scale. The pitch is simple: lower compute bills and lower energy use for businesses deploying AI. DeepInfer is now available on GitHub under the Apache 2.0 license. That is a permissive open-source license, so companies can use and modify the code in commercial products.
Source: Crypto Briefing
