Our inference stack, optimized for Blackwells, with a novel attention kernel and many new optimizations has start…

Our inference stack, optimized for Blackwells, with a novel attention kernel and many new optimizations has started rolling out! It's already charting on Artificial Analysis, eg: #1 speed and latency for @Kimi_Moonshot Kimi 2.6. #1 on l
Ranked #31 on backlist 2026-05-24 (24 May 2026 UTC) · by (Vipul Ved Prakash) ·

How it ranks: Backlist reads my Twitter/X timeline, scores every tweet for substance with an LLM rubric (not engagement), and publishes the daily top picks with a one-line takeaway. Curated by Surya Dantuluri.