DeepSeek open-sources the inference engine behind its API. And Huawei gets equal billing with Nvidia.
DeepSeek has open-sourced the inference engine it uses to serve its models in production, a step it said last year The post DeepSeek open-sources the inference engine behind its API. And Huawei gets equal billing with Nvidia. appeared first on The New Stack .
DeepSeek has recently made its inference engine, named DeepInfer, open-source. This move comes after the company had previously stated that it was not yet ready to share such technology. DeepInfer is designed to allow developers to run DeepSeek's V4.1 Flash model on their own infrastructure with optimized performance. The framework includes support for future DeepSeek models and offers features like speculative decoding and asynchronous scheduling for faster response generation.
Open-sourcing DeepInfer is part of DeepSeek's effort to make AI more affordable by reducing compute costs and energy use.
Written by urgent.news from The New Stack's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
