AI at AMD(@AIatAMD):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.

AI at AMD

@AIatAMD

Advancing AI innovation together. Built with devs, for devs. Supported through an open ecosystem. Powered by AMD. #TogetherWeAdvance#

Joined November 2016

116 Following 59.6K Followers

AI at AMD@AIatAMD

2026.10.27 16:58

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.

491

Forward to community

Most Popular Users