Topic

Sparse Attention

All digests tagged Sparse Attention

Suggested route

Topic journey

Move from earlier context through the available material to the newest signals. This route is a reading aid, not a difficulty ranking.

Start here

How MiniMax M3 Was Built: Sparse Attention and Native Multimodality — Olive Song Oct 10, 2026 · 15:03 MiniMax M3 combines agentic coding, 1M context, and native multimodality. The model uses MSA sparse attention, achieving 9x faster pre-fill and 15x faster decode vs. full attention.

AI Engineer

How MiniMax M3 Was Built: Sparse Attention and Native Multimodality — Olive Song

MiniMax M3 combines agentic coding, 1M context, and native multimodality. The model uses MSA sparse attention, achieving 9x faster pre-fill and 15x faster decode vs. full attention.

Read article