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

开发者把 Arch Linux 移植到 RTX Spark 笔记本,116GiB 统一内存直通 CUDA

AI 总结

一位 Arch Linux 软件包维护者在个人博客中记录,他将 Arch Linux ARM 移植到 ASUS ProArt P16(128GB 内存、6144 CUDA 核心、NVIDIA N1X GPU 的 RTX Spark 笔记本),并公开了可启动安装方法与补丁。他自测 7-Zip 单线程成绩与公开的 Windows 结果基本持平,20 线程压缩约快 5%、解压约快 3%,但对比机型所用的 7-Zip 版本与字典大小并不一致。在本地推理测试中,他的 Linux 配置以 Qwen3.8-Flash-Next 跑出约 30.9 tokens/s,并称 171 次测量回答全部通过校验,十分钟循环中位响应时间增幅不到 1.6%。

深度见解

作者称其 Linux 环境把同一块 116.0 GiB 物理内存池同时报告给操作系统和 CUDA,而按 NVIDIA 移植指南,Windows 会把内存划分为独立 GPU、共享与纯 CPU 区域。

tl;dr - boo hoo microsoft bad. Arch Linux works, keeps up with Windows in 7-Zip, and reports the same 116.0 GiB memory pool to the OS and CUDA. My initial bootable setup and patches are here. This is for the ASUS ProArt P16 H7607BA-SE033W: the 128 GB RAM configuration with 6,144 CUDA cores and a 2 TB SSD.

Image 1: Fastfetch showing Arch Linux ARM on the ASUS ProArt P16 with an NVIDIA N1X GPU.

When rumours started circulating about a laptop with over 100 GiB of RAM the GPU could access, I started thinking about all the things I could build on it and all the optimisations I could spend far too long playing with. I'm very pro open-weight models. Being able to run things locally and mess around with RL, quantisation and fine-tuning on a laptop would be sick. I already publish my own GGUF quants on Hugging Face, with over 160,000 downloads in the past month.

#ASUS ProArt P16#Nvidia RTX Spark#NVIDIA N1X#Arch Linux ARM#Qwen3.8-Flash-Next#vLLM#Hugging Face#NVIDIA

原文约 6 分钟读完阅读原文
群聊

还没有评论,来说说你的看法。