DeepSeek just open-sourced its inference engine

Re:DeepSeek just open-sourced its inference engine by draxen on Tuesday October 20, 2026 @08:09AM (#50165101)

One of the fascinating dynamics around Chinese open-weights models is the competition among American (and some European) inference providers to deliver the best inference performance on them. They've increasingly beaten the Chinese model makers themselves on inference throughput and latency.

Together.ai, Baseten, and others have already achieved higher throughput, lower latency, and lower E2E latency for DeepSeek V4.1 Flash 1017 than DeepSeek's own inference service.

https://openrouter.ai/deepseek/deepseek-v4.1-flash-1017

[ Parent | on HN ]

Re:DeepSeek just open-sourced its inference engine by HoyaSaxa on Tuesday October 20, 2026 @08:20AM (#50165254)

That’s just likely the NVDA chip ban at play. I wouldn’t bet on that being an enduring truth

[ Parent | on HN ]

Re:DeepSeek just open-sourced its inference engine by JacobAsmuth on Tuesday October 20, 2026 @01:46PM (#50169995)

Why? Next gen chips are coming very soon (VR) and VR Ultra will follow, with Fyenman afterwards. Huawei will find it very difficult to compete with those products.

[ Parent | on HN ]

Re:DeepSeek just open-sourced its inference engine by desterothx on Tuesday October 20, 2026 @10:26AM (#50166955)

Well presumably the load on the deepseek inference service is a lot higher, probably most users of deepseek use it through them (presumably more in SEA, less in US/EU). And for the users from the EU/US, if they are going to use deepseek, their usage is distributed among all those providers (because of the need for zdr)

[ Parent | on HN ]

Re:DeepSeek just open-sourced its inference engine by russli1993 on Tuesday October 20, 2026 @11:16AM (#50167693)

these labs have access to far better NVIDIA chips than deepseek

[ Parent | on HN ]