Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Qwen-Image-2.1 Deployed on NVIDIA DGX Spark with GPUStack

AI summary

A Juejin AI author reports deploying Qwen-Image-2.1 on an NVIDIA DGX Spark with the GB10 GPU, 121GB unified CPU/GPU memory, and ARM64 architecture. The GPUStack-managed service exposed an OpenAI-compatible API for text-to-image generation, image editing, native transparent backgrounds, and LoRA; reported results included 49 seconds for a 1024×1024, 40-step generation and 38GB resident memory. The report also documents ARM64 image building, dependency isolation, network troubleshooting, deployment, and gateway configuration.

In-depth insight

The report presents a working ARM64 image-generation deployment on compact hardware, including an OpenAI-compatible API and documented deployment steps, though the claims come from a single source rather than independent corroboration.

一台 2025 年底上市的 ARM 小盒子。121GB 统一内存,一块 GB10,官方文档里写着这类模型跑不了它的架构。

现在它对外提供一个 OpenAI 兼容的图像接口,文生图、改图、原生透明底、LoRA 四项全通。硬件一点没动,驱动没升级,也没有第二台机器。

把镜像变成团队里人人能调的服务,中间那段是 GPUStack 接过去的。下面记录整个过程:先判断 ARM 到底能不能跑,再处理构建、网络、部署和网关问题。

01 · 文档说不支持,我先去验一句

机器是 DGX Spark,GB10,aarch64 架构。驱动 580.173.02,CUDA 13.0,121GB 内存由 CPU 和 GPU 共用。

项目实测环境
设备NVIDIA DGX Spark
GPUGB10
架构aarch64 / sm_121
驱动580.173.02
CUDA13.0
内存121GB CPU/GPU 统一内存

#Qwen-Image-2.1#NVIDIA DGX Spark#NVIDIA GB10#GPUStack#vLLM-Omni

Original · 13 min readRead the original
Group chat

No comments yet. Start the conversation.