← Back to the wire

Nunchux AI Introduces VC-Attention: A Training-Free Low-Bit Attention Kernel That Speeds Up Video Diffusion Transformers

AnnouncementModelSep 17, 2026

Nunchux AI released VC-Attention, a training-free low-bit attention kernel for video diffusion transformers. It pairs V-Smooth, which clusters value tokens and quantizes residuals after block-mean subtraction, with ExpCast-FP8, which replaces the FP32 exponential with a single multiply-add. Benchmarks report 6.02× speed over SageAttention2 on B200 and 1.60× over BF16 FlashAttention-4 on MiniMax-H3, with PSNR gains on Wan2.2-14B. No public kernel release yet.

Receipt № 19351 source · awaiting confirmation ◐

Evidence

1source· awaiting independent confirmation

No score is assigned. Sources and their independence are shown in the citation chain below.

Citation chain · 1 source

Nunchux AICompanyVC-AttentionModelWan2.2-14BModelMiniMax-H3Model
Canonical: https://www.marktechpost.com/2026/09/16/nunchux-ai-introduces-vc-attention-a-training-free-low-bit-attention-kernel-that-speeds-up-video-diffusion-transformers/