Nothing wrong - just for transparency. Also, the price difference is not quantif... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		DrNosferatu on June 13, 2024 \| parent \| context \| favorite \| on: AMD's MI300X Outperforms Nvidia's H100 for LLM Inf... Nothing wrong - just for transparency. Also, the price difference is not quantified. Additionally, CUDA is a known and tangible software stack - can I try out this "MK1 FLywheel" on my local (AMD) hardware?

muxr on June 16, 2024 [–]

None of those things matter, if all you're looking to do is run your existing workloads on mi300x in the cloud. You get more bang per buck by going AMD.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact