-
-
Notifications
You must be signed in to change notification settings - Fork 10.6k
[Misc] Manage HTTP connections in one place #6600
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Conversation
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, please make sure to run full CI as it is required to merge (or just use auto-merge). To run full CI, you can do one of these:
🚀 |
@simon-mo WDYT of this PR? I think it makes sense to me to unify the management of HTTP connections. |
Code style wise, I would prefer something like But good direction! |
See if f4cfb65 suits you. |
Any update? @simon-mo |
I'm not 100% sure how, but this PR appears to have broken the dev documentation. Setup environment: cd docs
python -m venv venv
. venv/bin/activate
pip install -r requirements-docs.txt Start HTTP server: python -m http.server -d build/html/ Checkout commit prior to this PR and build: git checkout c051bfe4eb77b82eba90504360bbd4e61d9e489a
make clean && make html Navigate to http://localhost:8001/dev/sampling_params.html and see a populated page. Checkout merge commit from this PR and build: git checkout 97234be0ec67f48ed5e65bc0290f329dfb33798e
make clean && make html Navigate to http://localhost:8001/dev/sampling_params.html and see an empty page. |
Signed-off-by: Alvant <[email protected]>
Signed-off-by: LeiWang1999 <[email protected]>
This PR adds
vllm.connections.HTTP_CONNECTION
so that we can reuse the same sync/async client session. It also encapsulates the boilerplate code for common uses ofrequests
andaiohttp
libraries.