logoalt Hacker News

tintortoday at 12:55 AM2 repliesview on HN

Airgapped LLM inferrence server can't serve their output tokens, right?


Replies

angry_octettoday at 1:09 AM

They can expose just their inference port, possible via some supervisor. The inference consumer can also be air gapped. This kind of segmentation is increasingly common for high value services.

show 1 reply
bibimsztoday at 1:32 AM

not at a high bitrate