test: Increase server startup timeout for vllm tests for test stability #101
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
… the model during server startup, compared to trtllm flow which downloads model as offline import step
rmccorm4
changed the title
rmccorm4
changed the title
krishung5
approved these changes
Jan 17, 2025
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Outdated suggestions cannot be applied.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 separate large timeout for vllm server startup since it downloads the model during server startup, compared to trtllm flow which downloads model as offline import step.
Before this change, the server startup timeout was 10min for vllm models, but sometimes this wasn't enough to fully download the model when network connection is slow. Even though the overall test timeout was set higher, the server startup would still timeout.
This change gives more timeout room for server startup when running vLLM test cases.