[feat] add disable_sliding_window parameter to vllm/lmi-dist engine args #2338
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
hommayushi3
commented
Aug 23, 2024
tosterberg
requested changes
Aug 23, 2024
tosterberg
approved these changes
Aug 25, 2024
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Outdated suggestions cannot be applied.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.
Description
Adds VLLM's
disable_sliding_windowparameter to vllm/lmi-dist engine args. This allows for using models like Phi-3-vision that specify a sliding window in their model config.json files to be used with Flash Attention 2 because vllm does not currently support flash attention with sliding window.Addresses #2337.