# LongLive-2.0: An NVFP4 Parallel Infrastructure for Long Video Generation

arXiv: https://arxiv.org/abs/2605.18739 · HTML: https://mlsanity.com/paper/2605.18739/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Placed in Video generation, one of 14 directions in Diffusion models.
- Builds on 76 of its 82 references that are in the map.
- First posted on arXiv 18 May 2026.

## Placed in

- Diffusion models / [Video generation](https://mlsanity.com/diffusion/video-generation/)
- Efficient LLM inference and serving / [Fast autoregressive visual generation](https://mlsanity.com/inference/fast-autoregressive-visual-generation/)

## Builds on (most cited first, 30 of 76)

- [Scalable Diffusion Models with Transformers](https://mlsanity.com/paper/2212.09748/) (2022)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [GPTQ: Accurate Post-Training Quantization for Generative Pre-trained Transformers](https://mlsanity.com/paper/2210.17323/) (2022)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models](https://mlsanity.com/paper/2211.10438/) (2022)
- [Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion](https://mlsanity.com/paper/2407.01392/) (2024)
- [Autoregressive Image Generation without Vector Quantization](https://mlsanity.com/paper/2406.11838/) (2024)
- [QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs](https://mlsanity.com/paper/2404.00456/) (2024)
- [Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion](https://mlsanity.com/paper/2506.08009/) (2025)
- [KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization](https://mlsanity.com/paper/2401.18079/) (2024)
- [Latte: Latent Diffusion Transformer for Video Generation](https://mlsanity.com/paper/2401.03048/) (2024)
- [MANIQA: Multi-dimension Attention Network for No-Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08958/) (2022)
- [Ring Attention with Blockwise Transformers for Near-Infinite Context](https://mlsanity.com/paper/2310.01889/) (2023)
- [From Slow Bidirectional to Fast Autoregressive Video Diffusion Models](https://mlsanity.com/paper/2412.07772/) (2024)
- [Pyramidal Flow Matching for Efficient Video Generative Modeling](https://mlsanity.com/paper/2410.05954/) (2024)
- [LongVILA: Scaling Long-Context Visual Language Models for Long Videos](https://mlsanity.com/paper/2408.10188/) (2024)
- [MAGI-1: Autoregressive Video Generation at Scale](https://mlsanity.com/paper/2505.13211/) (2025)
- [LongLive: Real-time Interactive Long Video Generation](https://mlsanity.com/paper/2509.22622/) (2025)
- [Rolling Forcing: Autoregressive Long Video Diffusion in Real Time](https://mlsanity.com/paper/2509.25161/) (2025)
- [SkyReels-V2: Infinite-length Film Generative Model](https://mlsanity.com/paper/2504.13074/) (2025)
- [LCM-LoRA: A Universal Stable-Diffusion Acceleration Module](https://mlsanity.com/paper/2311.05556/) (2023)
- [FP8 Formats for Deep Learning](https://mlsanity.com/paper/2209.05433/) (2022)
- [Self-Forcing++: Towards Minute-Scale High-Quality Video Generation](https://mlsanity.com/paper/2510.02283/) (2025)
- [Autoregressive Video Generation without Vector Quantization](https://mlsanity.com/paper/2412.14169/) (2024)
- [Flex Attention: A Programming Model for Generating Optimized Attention Kernels](https://mlsanity.com/paper/2412.05496/) (2024)
- [Causal Forcing: Autoregressive Diffusion Distillation Done Right for High-Quality Real-Time Interactive Video Generation](https://mlsanity.com/paper/2602.02214/) (2026)
- [SVDQuant: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models](https://mlsanity.com/paper/2411.05007/) (2024)
- [SageAttention: Accurate 8-Bit Attention for Plug-and-play Inference Acceleration](https://mlsanity.com/paper/2410.02367/) (2024)

## Built on by (most cited first, 30 of 30)

- [Infinite Worlds with Versatile Interactions](https://mlsanity.com/paper/2607.07534/) (2026)
- [Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models](https://mlsanity.com/paper/2606.25473/) (2026)
- [Self Gradient Forcing: Native Long Video Extrapolation](https://mlsanity.com/paper/2607.20368/) (2026)
- [ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU](https://mlsanity.com/paper/2607.19191/) (2026)
- [ReWorld: An Interactive World Model with Long-Horizon Memory](https://mlsanity.com/paper/2608.23565/) (2026)
- [Sol Video Inference Engine: Agent-Native Full-Stack Acceleration Framework for Efficient Video Generation](https://mlsanity.com/paper/2606.23743/) (2026)
- [Stream3D: Sequential Multi-View 3D Generation via Evidential Memory](https://mlsanity.com/paper/2605.21472/) (2026)
- [JoyAI-Video-Edit: Real-Time Open-Ended Video Editing with Autoregressive Diffusion](https://mlsanity.com/paper/2608.03974/) (2026)
- [Wan-Animate-2: Pushing the Application Boundaries of Character Animation](https://mlsanity.com/paper/2608.06009/) (2026)
- [Zing-0.5: Toward Playable Worlds with Real-Time Joint Action and Text Control](https://mlsanity.com/paper/2609.17909/) (2026)
- [Magpie: Real-Time World Renderer for Interactive Games](https://mlsanity.com/paper/2608.27168/) (2026)
- [M4World: A Multi-view Multimodal Driving World Model for Interactive Object Manipulation and Minute-long Streaming](https://mlsanity.com/paper/2607.14005/) (2026)
- [Visko Orbis 1.0: A Live Model for Real-Time Interactive Long Video Generation](https://mlsanity.com/paper/2607.26694/) (2026)
- [EditStream: A Unified Autoregressive Framework for Interactive Video Generation and Editing](https://mlsanity.com/paper/2608.21424/) (2026)
- [FlashRT: Agent Harness for Guiding Agents to Deploy Real-Time Multimodal Applications](https://mlsanity.com/paper/2607.18171/) (2026)
- [Avatar-Forever: Decoupled Parallel Training for High-Quality Real-Time Infinite Avatars](https://mlsanity.com/paper/2608.12107/) (2026)
- [WorldCrafter: Consistent Video World Model with Implicit 3D-aware Memory](https://mlsanity.com/paper/2609.24984/) (2026)
- [Long-WAM: Scaling the Context of World-Action Models](https://mlsanity.com/paper/2610.10528/) (2026)
- [DreamForge-World 0.1 Preview: A Low-Compute Real-Time Controllable World Model](https://mlsanity.com/paper/2606.30292/) (2026)
- [InfinityEdit: Infinite Video Editing with a Lightweight Edit-Ignition Adapter](https://mlsanity.com/paper/2608.20910/) (2026)
- [UnStep: Training-Free Acceleration of Causal Video Diffusion with Fewer Steps Than Distillation](https://mlsanity.com/paper/2609.32518/) (2026)
- [Sol-H3: Recursive Self-Improvement for MiniMax-H3 Inference Acceleration on Sol-Engine across Cloud and Edge](https://mlsanity.com/paper/2609.35110/) (2026)
- [Complementary Retrieval-Augmented Prompting for Consistent Long-Form Video Generation](https://mlsanity.com/paper/2609.37407/) (2026)
- [No Corners Cut: State-Grounded Transitions for Mid-Stream Prompt Switches in Video Generation](https://mlsanity.com/paper/2609.38691/) (2026)
- [FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation](https://mlsanity.com/paper/2609.38839/) (2026)
- [Weave Forcing: Compositional Memory Routing for Interactive Long Video Generation](https://mlsanity.com/paper/2610.03510/) (2026)
- [ProAR: Learning Prospective Reasoning with Autoregressive Video Models](https://mlsanity.com/paper/2610.03664/) (2026)
- [CORAL-KV: Compact Cross-Layer Prediction and Residual Coding for Autoregressive Video KV Caches](https://mlsanity.com/paper/2610.12514/) (2026)
- [CineMem: Attention-Aligned Fine-grained Memory Retrieval for Multi-Shot Long Video Generation](https://mlsanity.com/paper/2610.17926/) (2026)
- [Long-horizon Video Generation with Slot Memory Addressed By Region Tokens](https://mlsanity.com/paper/2610.19257/) (2026)

## Abstract (arXiv)

We present LongLive-2.0, an NVFP4-based parallel infrastructure throughout the full training and inference workflow of long video generation, addressing speed and memory bottlenecks. For training, we introduce sequence-parallel autoregressive (AR) training, instantiated as Balanced SP, which co-designs the efficient teacher-forcing layout with SP execution by pairing clean-history and noisy-target temporal chunks on each rank, enabling a natural teacher-forcing mask with SP-aware chunked VAE encoding. Combined with NVFP4 precision, it reduces GPU memory cost and accelerates GEMM computation during training, the proportion of which increases as video length grows. Moreover, we show that a high-quality infrastructure and dataset enable a remarkably clean training pipeline. Unlike existing Self-Forcing series methods that rely on ODE initialization and subsequent distribution matching distillation (DMD), LongLive-2.0 directly tunes a diffusion model into a long, multi-shot, interactive auto-regressive (AR) diffusion model. It can be further converted to real-time generation (4 to 2 denoising steps) with standalone LoRA weights. For inference on Blackwell GPUs, we enable W4A4 NVFP4 inference, quantize KV cache into NVFP4 for memory savings, and boost end-to-end throughput with asynchronous streaming VAE decoding. On non-Blackwell GPU architectures, we deploy SP inference to match the speed on Blackwell GPUs, while the quantized KV cache can lower inter-GPU communication of SP. Experiments show up to 2.15x speedup in training, and 1.84x in inference. LongLive-2.0-5B achieves 45.7 FPS inference while attaining strong performance on benchmarks. To our knowledge, LongLive-2.0 is the first NVFP4 training and inference system for long video generation.