DeepSeek has made DeepInfer, the engine it says runs its large-scale AI services, free for anyone to use, though only part of it is released.
DeepSeek has released DeepInfer, the software it says powers its large-scale AI services, as a free download. The code went up on GitHub and drew 420 points and 139 comments on Hacker News. It is aimed at engineers, not everyday users.
Inference means running a finished AI model to produce answers. DeepInfer is the engine that does that work for DeepSeek models. It is free under the Apache 2.0 license. DeepSeek says it was built primarily on vLLM, with ideas from SGLang and TensorRT-LLM. The default model it runs is DeepSeek-V4.1-Flash-1017.
This release covers offline use only. The parts needed for a complete online service are not included, so it is not a full copy of what DeepSeek runs.
The material does not say how much money DeepInfer could save, or how it compares with other tools. DeepSeek lists its own speed tests, measured on 4 NVIDIA-class chips for one stage and 64 for another. For most businesses, the practical effect would come later, if free tools like this lower the cost of AI features built into the software they use.
DeepInfer is a free but partial release for engineers, and any lower AI costs for ordinary businesses would come later, if at all.
A new Alibaba-led test of real coding requests found the best AI agent fully finished just 26.4 percent of tasks, so human review still matters.
Read more: AI coding helpers fully finish only about 1 in 4 real tasksEA has re-released 25 classic PC games at a discount until November 19, and Bethesda has finally given The Elder Scrolls VI a subtitle: Sentinel.
Read more: EA brings 25 classic PC games back, and Elder Scrolls VI gets a nameA user says Anthropic's Claude Code put his email in web requests, then scam messages arrived. The link is unproven, but it shows what AI tools can share.
Read more: User says Claude Code sent his email address to websites
