fix: Avoid thread starvation on many concurrent requests by making use of asyncio to lock llama_proxy context #1798
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
gjpower
force-pushed
the
fix/server_llama_call_thread_starvation
branch
from
8745712 to
de01a63
Compare
gjpower
force-pushed
the
fix/server_llama_call_thread_starvation
branch
from
de01a63 to
9ec5460
Compare
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Supersedes previous MR #1795
Previous implementation creates and locks threads when acquiring llama_proxy, this can cause thread starvation on many parallel requests.
This also prevents call to
await run_in_threadpool(llama.create_chat_completion, **kwargs)proceeding as all worker threads are stuck awaiting lock so no progress may be made.This MR adapts acquiring of llama_proxy to async pattern taking advantage of asyncio mechanisms. ExitStack is replaced with AsyncExitStack and improper closing of the ExitStack is addressed