Deepseek open-sources the inference engine that powers its fastest and cheapest AI model

Deepseek releases DeepInfer, an open‑source inference engine that powers its V4.1‑Flash model. The vLLM‑based framework cuts compute costs and energy use, making the model faster and cheaper. The move increases pricing pressure on major Western providers like OpenAI and Anthropic, encouraging more efficient inference solutions.

Opening Kapyn…