Share HuggingFace downloads between test runs #8
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
|
I haven't noticed any significant improvement for |
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Outdated suggestions cannot be applied.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.
The model tests take over 50 minutes, which is quite long and runs the risk of getting interrupted. This PR (ported from vllm-project/vllm#4874) attempts to reduce the running time by sharing the HuggingFace cache between test runs so that models need not be downloaded each time.
Please share any concerns you may have regarding this approach. I'm also not sure how to test the resulting speed-up since there is no guarantee that model tests are re-run in the same machine (and hence able to utilize the cache effectively).
Note:
hostPathvolumes in Kubernetes have associated security risks. Is there another way for agent-stack-k8s to use a persistent volume?