AI News
All stories
Reported

Zyphra reports 9 to 60x speedups at 10M tokens with subquadratic attention

Zyphra says it converted several models to its subquadratic attention and reports 9 to 60x speedups at 10M tokens, with Qwen losing under two RULER points at 1M.

Research · · 1 min read

Zyphra says that after converting several models to its subquadratic attention, they run 9 to 60 times faster at 10 million tokens. The company also reports that Qwen lost less than two points on the RULER benchmark at 1 million tokens. Both figures are Zyphra's own claims, presented as results from the converted models.

What changed

Zyphra says several models converted to its subquadratic attention run 9 to 60 times faster at 10 million tokens, with Qwen losing under two RULER points at 1 million tokens.

Type: Research · Applies to: Qwen

Why it matters

If the figures hold up outside the team's own tests, long-context workloads could become much cheaper to run.

Original source

We have no link to the original source for this story yet.

Where we saw it

1 source

Latent Space

Zyphra

AI wrote this summary from the sources listed, and nobody reviewed it individually before publication. Check the original source before you rely on it. How it works