Hacker News Reader

Comment by eigenspace | Hacker News Reader

I'm surprised they released this thing. Brand perception is probably a lot more important to Nvidia than whatever sales they could get from this thing, and if it's basically just DGX Spark, it's likely to underwhelm.

I've heard there's still a large backlog of both software problems, and hardware problems with the platform. The software problems could be fixed with time, but they'll still give a shitty first impression. I'd have thought Nvidia would just bury this and try again with a successor run of silicon with a new design.

This thing seems practically destined to just be a repeat of the Snapdragon laptop debacle.

View on HN

Speaking as someone who has had a DGX Spark all year and been active developing at the driver and kernel level for it and other ARM64 Linux devices the last couple of years, it's not bad now and certainly doesn't have any issues that I wouldn't expect to be fully fixed with the second-gen motherboards going into these. The main hardware issues are not with the core SoC. They're replaceable edge peripherals like the PD PMIC.

It has to work on day one whatever the Apple Mac M5 Ultra or Mac M6 Ultra are they will work well on day one, the cost of the laptop Spark probably in the thousands of dollars has to work from the start or its dead.

I cannot think why someone would run those workflows on a Windows laptop, unless someone has way too much money to spend.

> someone has way too much money to spend.

that's what nvidia is hoping for

If the workload is offloaded to the chip, why would the host platform matter?

Lots of machine learning workflows support Linux better than Windows, if they run on Windows at all. (e.g. https://docs.vllm.ai/en/latest/getting_started/quickstart/ )

DGX Spark runs Linux, and nobody is going to install Windows on that machine. This laptop got it backwards.

If someone decides to run Ollama for local inference with this laptop, they fit perfectly into the "has too much money to waste" bracket, which is addressed by a few other comments in the discussion.

WSL

Believe it or not, Windows (WSL) is the best Linux distro and Nvidia knows that.

It often works, but you always lose something compared to native Linux.

Nah, before WSL I was already using a mix of Virtual Box and VMware Workstation, between home and work computers.

Installing Linux natively on laptops has always had some specific features not working.

Even my Asus netbook, which came with Linux pre-installed, had wlan issues that I learned to work around with, and the driver never supported the same OpenGL version as the Windows one (3.3 vs 4.1).

My comment was saying you lose something (e.g. performance) when using WSL2 compared to native Linux on a proper workstation.

Linux driver has always been an issue on laptops, but that's not the concern for running Python code.

vllm-windows works well enough

There is vllm-windows, and it's just as fast as on Linux. BTW I'm the maintainer of triton-windows.

Reply on news.ycombinator.com