Just finished some benchmarks, I can confirm that Azure's GPT-3.5 endpoint is at least 3x faster than OpenAI's endpoint. I can't believe I'm saying this, but it's time to switch to Azure. Just updated my oss prompt eng & guardrails lib to support Azure: https:// github.com/dzhng/llamaflow
Just finished some benchmarks, I can confirm that Azure's GPT-3.5 endpoint is at least 3x faster than OpenAI's endpoint. I can't believe I'm saying this, but it's time to switch to Azure. Just updated my oss prompt eng & guardrails lib to support Azure: https:// github.com/dzhng/llamaflow