Distilling video generation models to extremely low inference budgets (e.g., 2--4 NFEs) is crucial for real-time deployment, yet remains challenging. Trajectory-style consistency distillation often becomes conservative under complex video dynamics, yielding an over-smoothed appearance and weak motion. Distribution matching distillation (DMD) can recover sharp, mode-seeking samples, but its local training signals do not explicitly regularize how denoising updates compose across timesteps, making composed rollouts prone to drift. To overcome this challenge, we propose Self-Consistent Distribution Matching Distillation (SC-DMD), which explicitly regularizes the endpoint-consistent composition of consecutive denoising updates. For real-time autoregressive video generation, we further treat the KV cache as a quality parameterized condition and propose Cache-Distribution-Aware training. This training scheme applies SC-DMD over multi-step rollouts and introduces a cache-conditioned feature alignment objective that steers low-quality outputs toward high-quality references. Across extensive experiments on both non-autoregressive backbones (e.g., Wan~2.1) and autoregressive real-time paradigms (e.g., Self Forcing), our method, dubbed \textbf{Salt}, consistently improves low-NFE video generation quality while remaining compatible with diverse KV-cache memory mechanisms. Source code will be released at \href{https://github.com/XingtongGe/Salt}{https://github.com/XingtongGe/Salt}.

翻译：将视频生成模型蒸馏至极低推理预算（例如2–4次NFE）对于实时部署至关重要，但仍面临挑战。轨迹式一致性蒸馏在复杂视频动态下往往趋于保守，导致生成结果过度平滑且运动表现力不足。分布匹配蒸馏（DMD）虽能恢复锐利且贴合模式的样本，但其局部训练信号未明确约束去噪更新在时间步之间的组合方式，致使组合式轨迹容易产生漂移。为解决这一问题，我们提出自洽分布匹配蒸馏（SC-DMD），该方法显式约束连续去噪更新在端点一致性上的组合。针对实时自回归视频生成，我们进一步将KV缓存视为参数化的质量条件，并提出缓存分布感知训练策略。该训练方案在多步轨迹上应用SC-DMD，并引入缓存条件化的特征对齐目标，引导低质量输出向高质量参考对齐。在非自回归骨干网络（如Wan~2.1）与自回归实时范式（如Self Forcing）的广泛实验中，我们的方法（命名为**Salt**）持续提升了低NFE视频生成质量，同时保持了与多种KV缓存内存机制的兼容性。源代码将于\href{https://github.com/XingtongGe/Salt}{https://github.com/XingtongGe/Salt}发布。