DeepSeek open-sources DeepInfer inference framework
DeepSeek announced on October 20 that it was open-sourcing DeepInfer, a framework for high-throughput, low-latency online inference of its large models. Its accompanying technical report said DeepSeek V4.1 Flash served 155 trillion tokens per day from a single cluster and generated US$38 per card-hour at the valley rate. These throughput and revenue figures are vendor claims that the supplied report does not independently verify.
DeepInfer exposes infrastructure that DeepSeek says powers its production inference services, while the reported cluster metrics provide a direct view into the framework's claimed operating scale.
This source is a digest of several news items (“【数智周报】MiniMax港股破发；DeepSeek开源推理框架DeepInfer并披露收入账…”). Find this story in the original.