MoonshotAI unveils Kimi's large-scale LLM serving architecture | Hacker News

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

		MoonshotAI unveils Kimi's large-scale LLM serving architecture (arxiv.org)
		18 points by slothfulhamster on July 2, 2024 \| hide \| past \| favorite \| 1 comment

ervinxie on July 2, 2024 | [–]

I have been wondering the reason why online generative AI can serving so many requests. This really gives me an explanation.

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