AI 导读
DeepSeek 宣布自研推理框架 DeepInfer 完全开源，Apache 2.0 协议，代码在 github.com/deepseek-ai/DeepInfer。该框架支撑 DeepSeek-V4.1-Flash 的规模化推理，主打高吞吐低延迟，官方称可帮助社区降低算力成本与能耗。Thomas Wolf 指出这是 DeepSeek 继 FlashMLA、DeepEP、DeepGEMM、3FS 之后又一次生产栈开源。
推荐理由
作者把 DeepSeek 历次开源组件串成一条线，读者可以据此看清其生产级推理栈的完整版图。
正文
DeepSeek's open-source streak is getting absurd:
- FlashMLA: 580 TFLOPS attention on H800
- DeepEP: MoE comms
- DeepGEMM: 1350+ FP8 TFLOPS matmul
- 3FS: they built an entire file system
- and today: the full inference engine behind V4.1-Flash, Apache 2.0
Mad respect
🚀 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：Thomas Wolf · x.com