ByteBrief
We're a portrait publication through and through. Turn your phone back and your briefing picks up right where you left it.
(We tried widescreen once. It wasn't us.)
DeepSeek open-sourced DeepInfer, the inference framework powering DeepSeek-V4.1-Flash, under the Apache 2.0 license. The release includes a separate MIT-licensed deepseek-recipe layer for token encoding. The system runs on NVIDIA SM100 GPUs and Huawei Ascend 950 NPUs, supporting a 1M-token context window.
Tap to vote and see what everyone thinks.
Summary by ByteBrief

DeepSeek Opens DeepInfer Engine to Public

DeepSeek open-sources DeepInfer, its internal production stack designed to accelerate inference, optimize chip performance, and reduce energy and compute costs (Saritha Rai/Bloomberg)

OpenCode Makes DeepSeek V4.1 Flash Free