You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Currently the fix is to shield process_prompt however this also makes it so that if a chatgpt api request times out, it never gets cancelled even when a download is not in progress.
This can lead to behaviour where exo keeps generating even after a chatgpt api request has timed out.
Gotchas: make sure however exo works right is actually cancellable end-to-end. If an inference is in progress, that needs to be cancellable - InferenceEngines need to support this behaviour.
The text was updated successfully, but these errors were encountered:
See #305
Currently the fix is to shield
process_prompt
however this also makes it so that if a chatgpt api request times out, it never gets cancelled even when a download is not in progress.This can lead to behaviour where exo keeps generating even after a chatgpt api request has timed out.
Gotchas: make sure however exo works right is actually cancellable end-to-end. If an inference is in progress, that needs to be cancellable - InferenceEngines need to support this behaviour.
The text was updated successfully, but these errors were encountered: