Comment by tintor 10 hours ago Airgapped LLM inferrence server can't serve their output tokens, right? 3 comments tintor Reply angry_octet 10 hours ago 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. what 7 hours ago Then it’s not air gapped… bibimsz 10 hours ago not at a high bitrate
angry_octet 10 hours ago 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. what 7 hours ago Then it’s not air gapped…
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.
Then it’s not air gapped…
not at a high bitrate