AMD MI355X vLLM performance on MiniMax M3.1 Flash jumps 4x in under 20 days
AnushElangovan · x · 2026-11-18
SemiAnalysis reports that vLLM performance on AMD MI355X running MiniMax M3.1 Flash improved 4x in under 20 days, thanks to new deterministic AMD kernels written in FlyDSL by Inferact that avoid atomic adds for output accumulation. The TCO chart shows tokens per $1 rising 2.55x–4.04x across the interaction range between Oct 23 and Nov 12, with MI355X ownership at $1.5/chip/hr at hyperscaler volume.
More from Infra
- AMD CEO Lisa Su on Nvidia's Jensen Huang turmoil: "The noise will work itself out" — adariostrange · 2026-11-18
- Rival Scraped Pickle Moose With 11,214 Rotating IPs From 148 Countries; Now Patched — AJChadha · 2026-11-18
- AWS CEO: Nvidia partnership will continue as we build our own Trainium chips — Kr00ney · 2026-11-18
- Amazon CEO Jassy: data center buildout is a must, stopping would be a historic mistake — Kr00ney · 2026-11-18
- Blackstone warns Anthropic will debut as junk-rated after record IPO, clouding $63B chip financing — deliprao · 2026-11-18
- US officials: Megaspeed probed since 2024, Nvidia put it on no-sell list in June 2025 — Eliv_nurotic · 2026-11-18