AI 导读
DeepSeek 宣布自研推理框架 DeepInfer 完全开源，用于以高吞吐低延迟支撑 DeepSeek-V4.1-Flash 的大规模推理服务，代码见 github.com/deepseek-ai/DeepInfer。
推荐理由
引用了知乎长文才有的单集群吞吐和每小时每卡收入数据，并据此对比 GPU 成本估算推理毛利率。
正文
deepseek posted way more alpha on their zhihu page, if you only read twitter you are reading the laowai approved stuff
"Based on this framework, we have implemented a high-throughput, low-latency large-scale inference service for DeepSeek V4.1 Flash. Currently, the service throughput of a single cluster is 155 trillion tokens/day, and the overall revenue is $38 per card per hour (based on off-peak prices)."
it costs roughtly $5-10 per gpu hour so depseek is claiming 80% serving margin at THEIR prices lololololol
🚀 Introducing DeepInfer, our in-house inference framework, now fully open source! Powering DeepSeek-V4.1-Flash at scale with high throughput and low latency. We’re sharing our production stack to help the community lower compute costs, reduce energy use, and make AI more affordable. 🔗 http://github.com/deepseek-ai/DeepInfer 1/4在 X 查看被引用的帖子
来源：swyx · x.com