perf(trl): set a timeout on vllm client HTTP calls#5288
Open
tejasae-afk wants to merge 1 commit intohuggingface:mainfrom
Open
perf(trl): set a timeout on vllm client HTTP calls#5288tejasae-afk wants to merge 1 commit intohuggingface:mainfrom
tejasae-afk wants to merge 1 commit intohuggingface:mainfrom
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Add a timeout to HTTP requests in trl/generation/vllm_client.py to prevent indefinite hangs.
Reason: Network calls without a timeout can hang a worker indefinitely.
Validation:
/Users/tejasattarde/Desktop/gh-patchbot/.venv/bin/python -m py_compile trl/generation/vllm_client.py.Context: py-http-timeout at trl/generation/vllm_client.py:184.
Note
Low Risk
Low risk: only adds a fixed timeout to two
requests.getcalls to prevent indefinite hangs, without changing request payloads or response handling logic.Overview
Adds a 10s timeout to vLLM client HTTP health-check and world-size
GETrequests intrl/generation/vllm_client.py, preventing workers from hanging indefinitely when the server is unreachable or unresponsive.Written by Cursor Bugbot for commit e76f973. This will update automatically on new commits. Configure here.