SGLang says it now matches DeepSeek's DeepInfer engine on DeepSeek-V4.1-Flash

The SGLang project says its inference engine now matches DeepInfer, DeepSeek's own engine, on both prefill and decode for DeepSeek-V4.1-Flash. A few hours after vLLM made a similar claim, SGLang reported up to 1.04× DeepInfer's prefill throughput on 4× GB300 and 4× B300, and up to 7.4% decode throughput on 64× GB300.

SGLang also says it provides an end-to-end reproduction guide and a full serving stack for running the setup in production. The figures are SGLang's own and have not been independently checked. The post had about 149 likes on X by October 24.