TokenSpeed MLA 2 Launches on NVIDIA Vera Rubin, Speeding Kimi K3 Decoding by Up to 3.44x

LightSeek Foundation's TokenSpeed team released MLA 2, a decoding kernel optimized for NVIDIA Vera Rubin and designed for Kimi K3's long-context agent inference, delivering up to 3.44x faster decoding than on B200.

2026-10-16 ~ 2026-10-16 · 3 related posts

• TokenSpeed MLA 2 ships for Vera Rubin: up to 3.44× faster Kimi K3 decode — zhyncs42 · 2026-10-16
• TokenSpeed MLA 2 hits NVIDIA Vera Rubin: up to 3.44x faster decode vs B200 — zhyncs42 · 2026-10-16

1 near-duplicate retellings: zhyncs42