Deepseek 開源其最快且最便宜的 AI 模型的推理引擎
deepseek 開源 deepinfer，其推理框架，降低 ai 運行成本。
deepseek has open-sourced deepinfer, its inference framework, under the apache license 2.0. deepinfer is the serving software that enables deepseek's v4.1-flash model to generate responses quickly at scale. the framework is built on vllm with optimized compute kernels, distributed processing, and faster text generation techniques. deepseek also released deepseek-recipe, which replicates the token processing of its official api. this release aims to help the community lower compute costs, reduce energy use, and make ai more affordable. the move adds pricing pressure on western providers like openai and anthropic.