← Saturday, October 10, 2026InferencePaper

MC-Sparse reuses attention metadata to speed diffusion transformers without visible quality loss

huggingface.co by Jiarui Chen et al. Editor score 8/10

MC-Sparse groups similar queries for GPU execution and caches selected KV tokens and dense-to-sparse residuals across denoising steps; experiments report better dense-attention fidelity and larger speedups than sparse baselines. Its training-free approach targets the latency and quality trade-off in long-sequence generation.

What

MC-Sparse is a training-free framework for sparse attention in diffusion transformers, designed to retain fidelity at high sparsity.

Method

It groups similar queries, selects individual KV tokens, and reuses cached query groups, KV indices and residuals across denoising steps.

Why it matters

The paper reports faster denoising with negligible quality loss, including 1.80× speedup on Minimax-H3-Base and 2.32× for 3D asset generation.

Read on huggingface.co → Code · 31 stars

Headline, summary, brief and diagram are written by a model from the source's own text; the link, byline and numbers come from the source. Read the original before relying on a claim.