DeepSeek opens its inference engine, leaving service plumbing to developers

DeepSeek described DeepInfer, its inference framework for running DeepSeek models, in an October 20th post on DeepSeek's official X account. The project puts model-serving infrastructure alongside the open models DeepSeek has released, offering a view into how DeepSeek says it runs inference at scale. The available materials do not identify founder Liang Wenfeng as a DeepInfer builder or maintainer.