Show HN: Multi-region Vertex AI inference router with Cloud Run
1–3 of 3 posts
Re: Show HN: Multi-region Vertex AI inference router with Cloud Run
#2OP here. Seems there are a number of folks struggling with this. Happy to answer questions about the networking setup.
Re: Show HN: Multi-region Vertex AI inference router with Cloud Run
#3OP here. Seems there are a number of folks struggling with this. Happy to answer questions about the networking setup.
Why not use the global vertex ai endpoints instead of region balancing?
1. This is Google's own recommendation, despite the latency concerns
2. Some models are only available in the global region.
Where/why are folks struggling with this?