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

MarkTechPost
Read full post
Nunchux AI launched VC-Attention, a training-free low-bit attention kernel for video Diffusion Transformers that reduces value quantization error and accelerates the softmax stage, cutting generation time significantly.

More in Machine Learning

Machine Learning5 min read

Open-weight model developer Arcee AI reaches $1B-plus valuation with new funding

SiliconANGLE

Microsoft AI CEO criticises Anthropic over model ‘rights’

Covered by 3 sources
Machine Learning4 min read

Noetive launches with $41M to bring self-improving AI to factories and logistics

SiliconANGLE