无需训练即可加速视频生成，提升推理速度两倍。
Block Cascading: Training Free Acceleration of Block-Causal Video Models
- 利用部分去噪的上下文并行生成视频块，打破顺序依赖。
- 1.3B模型从16FPS提升至30FPS，14B模型从4.5FPS提升至12.5FPS。
- 适合追求高帧率且对质量要求高的交互式视频生成场景。
块因果视频生成存在显著的速度-质量权衡：1.3B模型仅能实现16 FPS，而14B模型则低至4.5 FPS，迫使用户在响应速度与生成质量间做出选择。块级级联通过无训练并行化显著缓解此问题。核心洞察在于：未来视频块生成无需完全去噪的当前块即可启动。通过使用前序块的部分去噪上下文开启生成，我们将原本串行的流水线转化为可并行的级联结构。在5张GPU上利用时间并行性，所有模型规模均实现约2倍加速：1.3B模型由16 FPS提升至30 FPS，14B模型由4.5 FPS提升至12.5 FPS。此外，块级级联消除了交互生成中上下文切换时约200ms的KV缓存开销。大量实验验证表明，在多个块因果流水线中，从块因果转向块级联推理，生成质量无显著下降。
原文摘要 · Abstract (English)
Block-causal video generation faces a stark speed-quality trade-off: small 1.3B models manage only 16 FPS while large 14B models crawl at 4.5 FPS, forcing users to choose between responsiveness and quality. Block Cascading significantly mitigates this trade-off through training-free parallelization. Our key insight: future video blocks do not need fully denoised current blocks to begin generation. By starting block generation with partially denoised context from predecessors, we transform sequential pipelines into parallel cascades where multiple blocks denoise simultaneously. With 5 GPUs exploiting temporal parallelism, we achieve ~2x acceleration across all model scales: 1.3B models accelerate from 16 to 30 FPS, 14B models from 4.5 to 12.5 FPS. Beyond inference speed, Block Cascading eliminates overhead from KV-recaching (of ~200ms) during context switches for interactive generation. Extensive evaluations validated against multiple block-causal pipelines demonstrate no significant loss in generation quality when switching from block-causal to Block Cascading pipelines for inference. Project Page: https://hmrishavbandy.github.io/block_cascading_page/
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。