@berryxia· @berryxia · X·· 2026-05-20精选AI 评分65
AI 导读
NVIDIA 研究员 Yukang Chen 开源了 LongLive 2.0,一套端到端长视频生成基础设施,训练与推理都以 FP4 量化和并行加速为核心。该方案在 5B 模型上达到 45.7 FPS,并支持真实视频训练、few-step 蒸馏、多 shot 训练与推理、序列并行、NVFP4 KV cache 和异步 VAE 解码部署。
推荐理由
开源方案把 FP4 量化与并行加速同时用在训练和推理,读者可据此了解长视频实时生成的技术路线。
正文
兄弟们,NVIDIA研究员Yukang Chen刚刚把LongLive 2.0直接开源了!
这是全球第一个端到端、支持4-bit的超长视频生成基础设施,训练和推理全流程打通。
核心技术:FP4量化 + 并行加速,在5B模型上硬生生跑到45.7 FPS!
它还能做真实视频训练、few-step蒸馏、多shot训练/推理、序列并行、NVFP4 KV cache、异步VAE解码部署……
全套高效打法一次给你安排明白。
以前做长视频生成,要么慢得要死,要么只能生成短片,现在NVIDIA直接把4-bit长视频实时生成推向开源。
代码见评论区👇
🚀 Excited to release LongLive 2.0! 🎬 An end-to-end infrastructure for long video generation, with FP4 and parallelism at the core of both training and inference. ⚡45.7 FPS generation speed on 5B model⚡ ✨ LongLive 2.0 supports real-video training, few-step distillation, multi-shot training/inference, sequence-parallel acceleration, NVFP4 KV cache, and async VAE decoding deployment. 🧩 To our knowledge, this is the first open-source 4-bit long video generation infra that covers both training and inference. 🙌 Welcome to check it out, try it, and share feedback! 🔗 Code: github.com/NVlabs/LongLive 📰 Paper: huggingface.co/papers/2605.1… 🎥 Demo: nvlabs.github.io/LongLive/Lo… #LongVideoGeneration #VideoGeneration #Realtime #AIInfra #EfficientAI #FP4 #Parallel #NVIDIA Video在 X 查看被引用的帖子
来源:@berryxia · x.com