DeepSeek 开源 DeepInfer 推理框架，获 vLLM 致谢

发生了什么

DeepSeek 宣布推出 DeepInfer，这是其自研推理框架，为 DeepSeek-V4.1-Flash 提供大规模、高吞吐量和低延迟推理支持。 vLLM 感谢 DeepSeek 以 Apache 2.0 许可证发布该框架，并表示它最初主要基于 vLLM 构建；vLLM 计划借鉴其中的思路，以提升推理效率。 http://github.com/deepseek-ai/DeepInfer

3 家信源报道

这件事到目前为止

DeepSeek has open-sourced DeepInfer, its in-house inference framework, on GitHub, releasing the production stack it says powers DeepSeek-V4.1-Flash at scale. DeepSeek said the framework delivers high throughput and low latency, and that it aims to help the community lower compute costs, reduce energy use and make AI more affordable. vLLM thanked DeepSeek for releasing DeepInfer under the Apache 2.0 license and said the framework was initially built primarily on vLLM. The vLLM team said it plans to draw on DeepInfer’s ideas to improve inference efficiency.

继续阅读

正在热议

1. 2MiniMax 发布 M3.1 Flash，基准测试得分更高，任务成本低于 M3
2. 3Anthropic承诺将其5%的股份投入新设公益基金