# mit-han-lab/streaming-vlm

StreamingVLM: Real-Time Understanding for Infinite Video Streams

Repository: https://github.com/mit-han-lab/streaming-vlm
Canonical: https://ross.abutalabs.com/products/streaming-vlm
Language: Python
License: MIT
License Family: permissive
Last push: 2025-10-15T05:55:46+00:00

## Health v2 (maintenance only)
Score: 38/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 47, release rhythm 35, longevity 23
- inputs: {"age_days": 327, "days_push": 322, "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 1072, forks 66 (observed 2026-08-28T04:03:28.359401+00:00)

## What it is
StreamingVLM is a vision-language model framework from MIT Han Lab for real-time understanding of effectively infinite video streams. It maintains a compact KV cache with training aligned to streaming inference, avoiding quadratic cost and sliding-window pitfalls.

## Use cases
- understand infinite live video streams in real time
- run video question answering on long videos
- process hours-long video without quadratic attention cost
- benchmark long video understanding with OVOBench
- fine-tune a VLM for streaming video inference
- achieve real-time FPS video captioning on a single GPU

## When to choose
- you need stable real-time comprehension of very long or endless video feeds
- you want a research-grade streaming VLM with training and evaluation scripts
- you have GPU hardware like an H100 and need high-FPS video understanding

## When to avoid
- you only need short-clip video analysis with standard VLMs
- you lack GPU resources for inference or fine-tuning
- you need a production-ready turnkey product rather than research code

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, video-processing, llm-inference, rag
- domain: computer-vision, large-language-models, artificial-intelligence
- platform: python
- tags: vision-language-model, streaming-video, kv-cache, real-time-inference, video-understanding, research-code, video, gpu, linux

## Member repositories
- mit-han-lab/streaming-vlm (main) score 38

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:28.359401+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 2026-08-30T06:53:42.409404+00:00, confidence not recorded.
  - readme: https://github.com/mit-han-lab/streaming-vlm (fetched 2026-08-28T04:03:28.359401+00:00, sha 9676cca08695)
- Data as of 2026-08-30T08:39:29.467469+00:00.