←back to thread

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

(gpuopen.com)
103 points beckford | 3 comments | 06 Oct 25 13:15 UTC | HN request time: 0.199s | source
1. drnick1 ◴[10 Oct 25 05:18 UTC] No.45535560[source]▶
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.
replies(2): >>45536633 #>>45538193 #
2. Klaster_1 ◴[10 Oct 25 08:49 UTC] No.45536633[source]▶
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.
3. pjmlp ◴[10 Oct 25 12:27 UTC] No.45538193[source]▶
These instructions assume there is already a working OS where everything is supported.

Some of us consider modern IDEs and advanced debugging tools a much better support for development.

https://bitsavers.org/pdf/xerox/parc/techReports/CSL-89-4_UN...