# NVlabs/LongLive

Long Video Gen Infrastructure

Repository: https://github.com/NVlabs/LongLive
Canonical: https://ross.abutalabs.com/products/longlive
Homepage: https://nvlabs.github.io/LongLive
Language: Python
License: Apache-2.0
License Family: permissive
Topics: real-time, infra, long, nvfp4, parallel, video-generation
Last push: 2026-08-07T02:35:21+00:00

## Health v2 (maintenance only)
Score: 60/100 (v2, computed 2026-09-03T02:39:23.370411+00:00)
- activity 96, release rhythm 35, longevity 24
- inputs: {"age_days": 345, "days_push": 27, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2563, forks 248 (observed 2026-08-28T04:07:01.057049+00:00)

## What it is
LongLive is an NVIDIA research framework providing parallel training and inference infrastructure for real-time long video generation, using NVFP4/FP8 quantization, KV-cache optimizations, and multi-shot autoregressive techniques. It achieves real-time frame rates (45.7 FPS) for generating minute-long and interactive videos with diffusion models like Wan2.2 and SANA-Video.

## Use cases
- generate long videos in real time from text prompts
- train autoregressive video generation models with parallelism
- run FP4/FP8 quantized video diffusion inference on GPUs
- generate interactive videos that respond to prompts mid-stream
- distill video diffusion models for faster inference
- compress KV cache for ultra-long video generation

## When to choose
- you need real-time or interactive long video generation on NVIDIA GPUs
- you want to train or fine-tune video diffusion models with efficient parallel infrastructure
- you need quantized (NVFP4/FP8) inference for video generation throughput

## When to avoid
- you need simple one-off video generation without GPU infrastructure
- you work outside the PyTorch/NVIDIA CUDA ecosystem
- you need production video editing rather than generative video synthesis

## Facets
- artifact type: framework
- maturity: active
- function: video-processing, llm-inference, llm-training, gpu-computing, machine-learning
- domain: deep-learning, gpu-computing, artificial-intelligence
- platform: python
- tags: video-generation, diffusion-models, nvfp4, quantization, real-time-inference, kv-cache, parallelism, nvidia, video, gpu, linux, docker

## Member repositories
- NVlabs/LongLive (main) score 60

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:01.057049+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T02:23:28.329105+00:00, confidence not recorded.
  - readme: https://github.com/NVlabs/LongLive (fetched 2026-08-28T04:07:01.057049+00:00, sha 983bfc98e407)
  - homepage: https://nvlabs.github.io/LongLive (fetched 2026-08-29T10:05:56.954676+00:00, sha 7376c5d5469e)
- Data as of 2026-08-30T08:39:29.467469+00:00.