Docs: add production deployment guide for async servers (FastAPI/uvic…#3856
Open
Shubh3005 wants to merge 1 commit into
Open
Docs: add production deployment guide for async servers (FastAPI/uvic…#3856Shubh3005 wants to merge 1 commit into
Shubh3005 wants to merge 1 commit into
Conversation
This file contains hidden or 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Closes #3839
This PR adds the production deployment guide discussed in #3839.
Per the maintainer's note on that issue, the root cause is correctly framed here as a synchronous, CPU-bound
model.encode()call blocking the async event loop when called directly inside anasync defendpoint — not an OpenMP/asyncio conflict. The fix section covers runningencode()in FastAPI's thread pool (plaindefendpoint, orrun_in_threadpoolinsideasync def), with batching recommended where possible.OMP_NUM_THREADS/MKL_NUM_THREADS/TOKENIZERS_PARALLELISMare reframed as thread-oversubscription and fork-safety tuning rather than deadlock fixes, and theKMP_DUPLICATE_LIB_OKrecommendation has been dropped per the note that it can mask real errors.