Fixed VLLM Cache #881
Merged
Fixed VLLM Cache #881
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Outdated suggestions cannot be applied.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.
Previously, the VLLM HFClient used different URLs for different requests, messing up the cache. This PR copies the way that the HG TGI Client handles multiple URLs and ports, which is a wrapper call function that overrides the URL and port in kwargs to be the same for all calls to the LM from the instantiated class. Since the specific URL/port for the request is now ignored (as the cache ignores the arg parameter), the cache will store the results of the call regardless of the specific URL it was routed to. This leads to significantly better performance with multi-host VLLM models!