DeepSeek Open-Sources DeepInfer, its High-Performance V4.1-Flash Serving Stack

DeepSeek has open-sourced DeepInfer, the high-performance inference framework that powers its large-scale production services, under the Apache 2.0 license on GitHub. The framework targets DeepSeek-V4.1-Flash and supports both Nvidia SM100 GPUs and Huawei Ascend 950 NPUs, making DeepSeek's recent systems papers operational for developers.