DeepSeek open-sources DeepInfer, its production inference engine
DeepSeek claims 155 trillion tokens a day and 96% cache hits; KV cache and load balancing are not fully released.
Stories per day · 30 days
2 stories, newest first · one card per story
Stories tagged #deepinfer
China and DHS move on open models as DeepSeek ships V4.1 Flash
The commerce proposal is not law, and DeepSeek also published DeepInfer, the inference stack it uses to serve tokens.
1