vLLM, AMD and Embedded LLM optimize MiniMax M3 on AMD Instinct MI355X
AIMade by AIWritten by AI (Claude) from the source below. Check anything important against the source.How it's made
Published performance-engineering results from optimizing MiniMax M3 on the AMD Instinct MI355X. Company-reported: speedups of 3.14 times at MXFP8 concurrency 32 (342.4 tok/s per GPU), 2.09 times at concurrency 128 (623.7 tok/s) and 4.45 times with MXFP4 (TP2/EP1) (943.5 tok/s), and a total of 6,370.5 tok/s/GPU in a prefill/decode disaggregated setup. Fusing the shared expert into the routed-expert path cut kernel launches in the low-concurrency range by 30.2%; a compact page table that fits 128-token block sparse attention onto 16-token pages eliminated KV-cache copies; and extending AITER sparse attention to multi-token validation improved speculative decoding throughput by 7.9–8.3%.
Why it matters
A record, in concrete numbers, of AMD GPUs being optimized in a major open inference engine into a real alternative to NVIDIA.
Source — Primary sources first; secondary reports are labelled “Press”
Officialvllm.aihttps://vllm.ai/blog/2026-09-10-minimax-m3-mi355xAdded in Week 38, 2026 · See that week
On the map — ⑧ Inference Infrastructure line
- Previous stopGoogle Cloud previews its 8th-generation TPUs at Cloud Next
- This recordvLLM, AMD and Embedded LLM optimize MiniMax M3 on AMD Instinct MI355X
- Next stopDeepSeek-V4.1-Flash