Fix the problem of 1k prompts. #127
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
ggaaooppeenngg
force-pushed
the
1k-prompts
branch
from
7607c07 to
ec3eee7
Compare
|
Thanks for your contribution! 🎉 👍 Please fix the pre commit linting issues. |
This commit enhances the router's concurrency capabilities. Key changes: 1. Set `httpx.AsyncClient` max connections to unlimited to unblock the requests. 2. In `process_request`, overwrite host header for proxies routing by host. 3. Call `set_ulimit` in `main` to prevent uvicorn from dropping requests due to high FD count. Signed-off-by: Peng Gao <[email protected]>
ggaaooppeenngg
force-pushed
the
1k-prompts
branch
from
ec3eee7 to
0dfdb7c
Compare
|
@gaocegege Done! |
gaocegege
previously approved these changes
Feb 15, 2025
ApostaC
reviewed
Feb 16, 2025
Signed-off-by: Peng Gao <[email protected]>
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Outdated suggestions cannot be applied.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.
httpx client has a default max_connections(100) which will block the requests if the concurrency is over 100.
This commit enhances the router's concurrency capabilities. Key changes:
httpx.AsyncClientmax connections to unlimited to unblock the requests.process_request, overwrite host header for proxies routing by host.set_ulimitinmainto prevent uvicorn from dropping requests due to high FD count.