NVIDIA Cosmos 3 Edge 世界模型获 vLLM 第零天支持
NVIDIA发了能在设备上实时跑的世界模型，4B参数，15Hz控制机器人，vLLM直接就能用。
NVIDIA 发布 Cosmos 3 Edge，一个4B参数的设备端世界模型，基于自研Nemotron骨干从零训练。
模型采用双Transformer塔架构：自回归塔处理视觉/文本推理，扩散塔负责预测、生成和动作输出。在640×360分辨率下，单次推理可输出32个动作，于Jetson Thor上实现15Hz实时控制。
vLLM和vLLM Omni已提供即日支持，可用于机器人、自动驾驶和视觉代理。
🚀 Day-0 support for NVIDIA Cosmos 3 Edge on vLLM and vLLM Omni!
An open on-device world model that lets robots, AVs, and vision agents reason over live video and generate robot actions locally.
🧩 4B params, built on two transformer towers over a shared representation: an autoregressive tower for vision/text reasoning + a diffusion tower for prediction, generation, and action 🧠 Built on a custom Nemotron backbone, trained from scratch — NVIDIA authored a dedicated vLLM integration to bring it up 🎮 Robot-control resolution (640×360), 32 actions/inference, real-time 15 Hz control on Jetson Thor
Serve it on vLLM and vLLM Omni today.
This report is categorized under AITOP's "Models" desk, focusing on US frontier AI labs and Silicon Valley technology leaders. Within our cross-regional analytical framework, it directly maps to US-China foundation model benchmarks and commercialization comparison. Key entities and technical topics under continuous tracking include NVIDIA Cosmos 3 Edge, vLLM, world models, robots.
Source attribution: curated from vLLM (@vllm_project). Cross-source corroboration: 6 independent sources have covered this development (including marktechpost, NVIDIA AI, Aravind Srinivas), confirming industry-wide signal strength.
