DeepSeek Opens Its Production Inference System DeepInfer
DeepSeek published DeepInfer, the inference system its own AI services use, with core functionality packaged for outside deployment. It is built on vLLM with ideas from SGLang and TensorRT LLM, runs DeepSeek-V4.1-Flash, and supports the DSpark acceleration technology, but a KV cache system is not implemented. DeepSeek also released deepseek-recipe, which converts requests and outputs between third-party APIs and the official DeepSeek API format.