Adding 5min timeout to internal nginx proxy #670
Merged
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Overview
For TGI and vLLM, we use a nginx proxy to re-route prediction requests to the correct underlying path. Nginx, however, has a 60 second default timeout which affects longer generation requests. This PR updates this timeout to be 5 mins.
We use the
proxy_read_timeoutdirective here (instead ofproxy_send_timeout) as it sets the timeout for reading a response from the proxied server vs. setting a timeout for sending a request to the proxied server.Testing