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

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

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

在 arXiv cs.CV 阅读 →

• Blackwell GPUs
• LongLive-2.0
• NVFP4

• 基础设施
• 论文

AI 生成摘要 · Google Gemini · 来自 1 个来源。 我们如何撰写摘要 →