Together AI unveils Consistency Diffusion Language Models with up to 14.5x faster inference

Jul 11, 2026

Together AI has introduced Consistency Diffusion Language Models (CDLM), a post-training method that enables exact block-wise KV caching and reduces the number of refinement steps required. This approach achieves up to 14.5x latency improvements over standard diffusion language models without sacrificing output quality.

Why it matters: This development makes diffusion language models more practical for real-time applications by significantly reducing inference time while maintaining quality.

Full story at: Together AI Blog ↗