LongLive-2.0 infrastructure accelerates long video generation training and inference

Researchers have developed LongLive-2.0, a parallel infrastructure designed to optimize the training and inference of long video generation models. This system utilizes NVFP4 precision and sequence-parallel autoregressive training to reduce memory requirements and accelerate computations. For inference, LongLive-2.0 employs techniques like W4A4 NVFP4 inference and asynchronous streaming VAE decoding to achieve high throughput, demonstrating up to a 2.15x speedup in training and 1.84x in inference. AI

IMPACT Enables more efficient training and faster inference for long video generation models, potentially leading to wider adoption and new applications.

RANK_REASON The cluster contains an academic paper detailing a new infrastructure for long video generation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• Blackwell GPUs
• LongLive-2.0
• NVFP4

• infra
• paper

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →