Thank you for the validation. As much as I don't like NVIDIA's shenanigans on Li... | Hacker News

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

		pdimitar 5 months ago \| parent \| context \| favorite \| on: DeepSeek-v3.1 Thank you for the validation. As much as I don't like NVIDIA's shenanigans on Linux, having a local LLM is very tempting and I might put my ideological problems to rest over it. Though I have to ask: why two eGPUs? Is the LLM software smart enough to be able to use any combination of GPUs you point it at?

arcanemachiner 5 months ago | [–]

Yes, Ollama is very plug-and-play when it comes to multi GPU.

llama.cpp probably is too, but I haven't tried it with a bigger model yet.

SV_BubbleTime 5 months ago | [–]

Even today some progress was released on parallelizing WAN video generation over multiple GPUs. LLMs are way easier to split up.

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