Live data from Hacker News

A beginner's guide to deploying LLMs with AMD on Windows using PyTorch

gpuopen.com

11–20 of 48 posts

Re: A beginner's guide to deploying LLMs with AMD on Windows using PyTorch

#11
post #2

I have a philosophy for which I have mixed feelings because I like it in principle despite it making me worse off in some other ways: Devs should punish companies that clearly don't give a shit about them. When I see AMD, I think of a firm that heavily prioritized their B2B business over B2C. Not just gamers, but a lot of LLM enthusiasts have been calling AMD to offer something comparable to 4090/5090, and don't mess…

it's not only the support. they are unable to write good software.

period.

Re: A beginner's guide to deploying LLMs with AMD on Windows using PyTorch

#12
post #2

I have a philosophy for which I have mixed feelings because I like it in principle despite it making me worse off in some other ways: Devs should punish companies that clearly don't give a shit about them. When I see AMD, I think of a firm that heavily prioritized their B2B business over B2C. Not just gamers, but a lot of LLM enthusiasts have been calling AMD to offer something comparable to 4090/5090, and don't mess…

I kind of feel the same way, but my take may not be quite as cynical. The way I see it, some companies just act really stupid, and there's a lot more room for forgiveness when you suspect incompetence than active disregard. There's a lot of talk about how amazing Lisa Su is as a leader, and while it's true that she has executed brilliantly on the goals she dictated for the company, the record will show that those goa…

What will likely break the monopoly is a Chinese competitor producing a worse but usable product within the next couple of years. AMD will be the next Compaq.

Re: A beginner's guide to deploying LLMs with AMD on Windows using PyTorch

#13
Anyone might have any idea whether it's easy (and worth it) to use the NPU or GPU on an earlier gen AMD? I have a 7480u, and CPU interference is quite alright but I've been wondering if the iPGU (or inbuilt and presumably puny) NPU might have any advantages.

Re: A beginner's guide to deploying LLMs with AMD on Windows using PyTorch

#14
post #2

I have a philosophy for which I have mixed feelings because I like it in principle despite it making me worse off in some other ways: Devs should punish companies that clearly don't give a shit about them. When I see AMD, I think of a firm that heavily prioritized their B2B business over B2C. Not just gamers, but a lot of LLM enthusiasts have been calling AMD to offer something comparable to 4090/5090, and don't mess…

Luckily you have NVIDIA to fall back on, with their affordable, consumer-focused LLM chips...

Re: A beginner's guide to deploying LLMs with AMD on Windows using PyTorch

#15
post #2

I have a philosophy for which I have mixed feelings because I like it in principle despite it making me worse off in some other ways: Devs should punish companies that clearly don't give a shit about them. When I see AMD, I think of a firm that heavily prioritized their B2B business over B2C. Not just gamers, but a lot of LLM enthusiasts have been calling AMD to offer something comparable to 4090/5090, and don't mess…

What do you think about: https://unlockgpu.com/? I put it on hold because the shareholder resolutions has to propose some concrete board level changes - and it seems (or seemed a few months ago) that AMD really started implementing such changes.

Re: A beginner's guide to deploying LLMs with AMD on Windows using PyTorch

#16
post #4

If you can follow these instructions, then you are also able to install Linux and can work in an environment with first class support for development and AI.

Recently, I wanted to TTS a book with abogen. I main Windows and it does everything I want from it, mostly gaming and web dev. It didn't work with my 7900XTX because of Pytorch incompatibility. Even Zluda didn't help because it lacked a specific feature necessary for the app. I just want to use locally AI powered software. AMD/Windows combo sucks for this.

Re: A beginner's guide to deploying LLMs with AMD on Windows using PyTorch

#17
post #2

I have a philosophy for which I have mixed feelings because I like it in principle despite it making me worse off in some other ways: Devs should punish companies that clearly don't give a shit about them. When I see AMD, I think of a firm that heavily prioritized their B2B business over B2C. Not just gamers, but a lot of LLM enthusiasts have been calling AMD to offer something comparable to 4090/5090, and don't mess…

They love gamers, just not on GNu/Linux.

Playstation, XBox, Windows, gaming handhelds.

Re: A beginner's guide to deploying LLMs with AMD on Windows using PyTorch

#18
post #17
post #2

I have a philosophy for which I have mixed feelings because I like it in principle despite it making me worse off in some other ways: Devs should punish companies that clearly don't give a shit about them. When I see AMD, I think of a firm that heavily prioritized their B2B business over B2C. Not just gamers, but a lot of LLM enthusiasts have been calling AMD to offer something comparable to 4090/5090, and don't mess…

They love gamers, just not on GNu/Linux. Playstation, XBox, Windows, gaming handhelds.

The steam deck is famously Linux and uses AMD

Re: A beginner's guide to deploying LLMs with AMD on Windows using PyTorch

#19
post #18
post #17

Earlier quoted context omitted.

They love gamers, just not on GNu/Linux. Playstation, XBox, Windows, gaming handhelds.

The steam deck is famously Linux and uses AMD

GNU/Linux like proper laptops and desktops, not gaming handhelds.

100% of the gamers that don't overlap with FOSS folks, don't care SteamOS is somehow based on the Linux kernel, the Steam Runtime and a Win32/DirectX translation layer, otherwise there would not be games to play.

Re: A beginner's guide to deploying LLMs with AMD on Windows using PyTorch

#20
post #19
post #18

Earlier quoted context omitted.

The steam deck is famously Linux and uses AMD

GNU/Linux like proper laptops and desktops, not gaming handhelds. 100% of the gamers that don't overlap with FOSS folks, don't care SteamOS is somehow based on the Linux kernel, the Steam Runtime and a Win32/DirectX translation layer, otherwise there would not be games to play.

Calling a Linux distro Gnu/Linux today is wrong because the actual Gnu code running is such a small part of everything.

SteamOS uses Linux as much as Linux distros like Fedora and Arch and other Linux based systems like Android.

A lot of gamers are also FOSS folks although not as hardcore as RMS.

Post reply on HN