DeepSeek V4.1 Flash hits 2,100+ tokens/sec per user on 8× AMD MI355X

AI at AMD @AIatAMDOriginally posted 2026.10.28

Open original on X

2,100+ tokens/sec per user on DeepSeek V4.1 Flash, at full model quality, on 8× AMD Instinct MI355X. 🚀 Congrats to @lithos_ai on pushing the frontier of inference with persistent megakernels on AMD. Open hardware + instruction-level control = room to innovate.

This post quotes another post: “Lithos engine hits 2,100+ tok/s per user on DeepSeek V4.1 Flash with eight MI355X GPUs”