DeepSeek Open-Sourced the Engine That Runs Its Models – on Nvidia and Huawei Silicon Alike

Analysis

A frontier lab just gave away the engine that runs its own production services: Apache 2.0, Nvidia and Huawei silicon from one tree, and a scope that stops exactly where production serving starts.

The serving layer is where the real cost of inference lives. For a week the industry’s attention has been on the license layer, where four labs moved to gate commercial deployment of open-weight models at the $20M revenue gate. DeepSeek just moved the pressure to the runtime. The lab that competes on price has given away the engine that runs its own production services.

We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable.

That is DeepSeek’s framing, in the announcement that shipped the code at 09:30Z Tuesday. The release itself is narrower than “production stack” suggests and wider than anything the four license gates hand over. Start with the terms: the Apache 2.0 license on the engine carries no additional conditions and no revenue gate, and the weights of DeepSeek-V4.1-Flash-1017 ship under MIT. Four labs now require commercial service operators to negotiate unpublished terms above $20 million in revenue. DeepSeek requires nothing of the kind.

One tree, two silicon stacks

The DeepInfer repository carries the kernels DeepSeek runs in production, by the company’s account: FlashMLA, DeepGEMM, DeepEP, TileKernels, DeepSelect, and custom TileLang kernels, with confidence-scheduled…