Trending storyPast story
InstinctFlash: Run 5B world-action models in real time on Jetson Thor
1 report1 sourceupdated 7 days ago
What happened
Summary
General-Instinct 开源了一个叫 InstinctFlash 的推理引擎，专门给机器人模型用。它能在 NVIDIA Jetson Thor 这种边缘设备上，把一个 50 亿参数、负责从感知直接输出动作的模型跑到实时——从看到画面到算出动作，延迟压到了 11 毫秒。仓库目前是早期公开状态，代码和文档还在整理。正文没提支持哪些机器人平台、模型...
Coverage
Follow the reports to see the story from different sides.
Sep 22
- Hacker News front pagePickInstinctFlash: Run 5B world-action models in real time on Jetson Thor
General-Instinct open-sourced InstinctFlash, a high-performance inference runtime built for robotics models. It runs 5B-parameter world-action models in real time on an NVIDIA Jetson Thor edge device, with perception-to-action latency at 11 ms. The repo is an early public release—code and docs are still being assembled. The post doesn't spell out which robot platforms are supported, where to get model weights, or what other hardware is compatible beyond Jetson Thor.