🚀 Introducing DeepInfer, our in-house inference framework, now fully open source!

DeepSeek has open-sourced DeepInfer, its in-house inference framework, which powers DeepSeek-V4.1-Flash at scale with high throughput and low latency.

• The company says it is sharing its production stack so the community can lower compute costs, reduce energy use, and make AI more affordable.
• The framework is now fully open source, with DeepSeek pointing readers to a link for the code.