DeepSeek's DeepInfer model-serving software, open-sourced in October 2026, was built mainly on the open-source vLLM inference engine

On October 20, 2026 DeepSeek open-sourced DeepInfer, the in-house inference framework it uses to serve its models, under the Apache 2.0 license; at release it supported only DeepSeek-V4.1-Flash on Nvidia SM100 GPUs and Huawei Ascend 950 chips.