Revert control server to Flask instead of FastAPI #385
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Outdated suggestions cannot be applied.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.
While my intentions were good (to increase performance thanks to FastAPI and unify some code with the inference server), this changed caused quite a few issues due to the async nature of the new control server that led to some race conditions while patching and restarting the inference server.
For now, let's revert and get back to this once we can properly test it for these race conditions.
Integration tests: https://github.com/basetenlabs/truss/actions/runs/5370661024