创建

登录 ReadmeX

或

了解我们如何处理你的信息: 隐私政策

ReadmeX

陪你读懂 AI 动态

今天,想先了解什么?

选一份动态总结,或直接聊聊你的问题。

社区和关注动态总结只属于你自己。

资讯

NVIDIA Nemotron 3.5 Super VL登陆SageMaker

AI 总结

AWS宣布NVIDIA Nemotron 3.5 Super VL现已登陆Amazon SageMaker JumpStart,可通过SageMaker Studio或SageMaker Python SDK部署。该视觉语言模型支持图像、视频和文本输入,JumpStart提供用于优化推理的NVFP4权重和BF16参考权重;NVIDIA称其采用120B参数骨干、每token激活12B参数,并支持最长100万token上下文。

深度见解

此次发布让AWS用户可以直接部署面向文档智能、GUI理解、视频问答和多模态智能体应用的大型多模态模型,并可选择优化推理或定制训练所需的权重版本。

Today, we’re announcing that NVIDIA Nemotron 3.5 Super VL is available in Amazon SageMaker JumpStart. You can deploy it with a few steps in SageMaker Studio or with a few lines of the SageMaker Python SDK. Super VL is the vision-language model (VLM) in the NVIDIA Nemotron 3.5 family. It accepts images, video, and text as input and generates text.

The model pairs a 120B-parameter hybrid Mixture-of-Experts (MoE) language backbone with 12B active parameters and a C-RADIO vision encoder. It supports context lengths of up to 1 million tokens and includes a built-in Multi-Token Prediction (MTP) head that supports speculative decoding. You can configure reasoning per request.

NVIDIA built Super VL for document intelligence, GUI understanding for computer-use agents, video question answering, and multimodal agentic applications. JumpStart offers two variants: NVFP4, quantized from BF16 with quantization-aware distillation for optimized inference, and the BF16 full-precision reference weights. In this post, we walk through the model’s capabilities and the JumpStart deployment configurations. We then show the measured inference performance and demonstrate text, image, and video inference.

Model overview

Nemotron 3.5 Super VL is a 120B-parameter model with 12B active parameters per token. It combines a hybrid language backbone with a dedicated vision encoder.

#NVIDIA#NVIDIA Nemotron 3.5 Super VL#Amazon SageMaker JumpStart#Amazon SageMaker Studio#SageMaker Python SDK#C-RADIO#NVIDIA NeMo RL#NVIDIA NeMo Gym#NVIDIA Model Optimizer

原文约 11 分钟读完阅读原文
群聊

还没有评论,来说说你的看法。