Add read timeouts to llama-server clients so hangs fail fast #43
Reference in New Issue
Block a user
Delete Branch "llama-timeouts"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
The OpenAI client defaults to a 600s read timeout, so a wedged llama-server blocked requests for 10 minutes and never raised — meaning the existing with_fallbacks() to OpenAI never triggered.