DeepSeek 开源推理框架 DeepInfer 和 deepseek-recipe
Deepseek open-sources the inference engine that powers its fastest and cheapest AI model
DeepSeek 将内部推理框架 DeepInfer 以 Apache License 2.0 开源，用于支持 V4.1-Flash 模型快速、大规模生成回答。DeepInfer 基于 vLLM，加入优化计算内核、多芯片分布式处理和更快的文本生成技术；DeepSeek 还发布 deepseek-recipe，用于复现官方 API 的 token 处理方式，让自托管部署的行为保持一致。
DeepInfer 与 deepseek-recipe 分别覆盖推理服务和 API token 处理复现，为自托管 DeepSeek 模型提供了降低计算成本的工具。
Deepseek has open-sourced DeepInfer, its internal inference framework, under the Apache License 2.0. Inference is how a trained AI model handles requests and generates responses. DeepInfer is the serving software that lets Deepseek's V4.1-Flash model produce answers quickly at scale.
The framework builds on vLLM with optimized compute kernels, distributed processing across multiple chips, and faster text generation techniques. Code for future Deepseek models will also ship as open source. Deepseek is also releasing deepseek-recipe, which replicates the token processing of the official Deepseek API so self-hosted setups behave the same way.
Deepseek's models are already dirt cheap. DeepInfer fills the last gap for running them even more cheaply. The goal is "to help the community lower compute costs, reduce energy use, and make AI more affordable," the company said on X. But the release also adds pricing pressure on Western providers like OpenAI and Anthropic. Given the AI race between China and the US, the move could be politically motivated too. If Western AI companies miss their growth targets, that's a risk for the US economy and beyond.
AI News Without the Hype – Curated by Humans
Subscribe to THE DECODER for ad-free reading, a weekly AI newsletter, our exclusive "AI Radar" frontier report six times a year, full archive access, and access to our comment section.
来源：The Decoder · the-decoder.com