NVIDIA SANA Sol Engine cuts MiniMax H3 768p latency to 14.93s

NVIDIA SANA team's Sol Engine work on MiniMax H3 reduced 10s 768p generation latency on a single GB200 from 414s to 14.93s using a 4-step low-res draft and 3-step LTX refinement with Sol-Attn.

This update bears on 2 kinds of work in 1 markets. Highest level accepted: L1 Assisted.

Highest accepted

L1Assisted

Work

2

Markets

1

Views

79.5K

The work it bears on

Highest level first. Open a kind of work to see everything else that moved it.

• L1Assisted
  Develop algorithms and study computational propertiesComputing and engineering research
  L1 AssistedConfirmed by several sources
• L1Assisted
  Build research prototypes and run comparative experimentsComputing and engineering research
  L1 AssistedConfirmed by several sources

Published at