Temporarily disable prefix caching on Metal#187
Merged
WindChimeRan merged 1 commit intovllm-project:mainfrom Mar 21, 2026
Merged
Conversation
Signed-off-by: kingwl <kingwenlu@gmail.com>
WindChimeRan
approved these changes
Mar 21, 2026
Collaborator
WindChimeRan
left a comment
WindChimeRan
left a comment
There was a problem hiding this comment.
Two non-blocking questions:
-
For dev purposes, should we add an env var override (e.g.
VLLM_METAL_FORCE_PREFIX_CACHING=1) so we can test the prefix caching path while it's disabled by default? We'll need to develop this soon. (This is an open question. Maybe you have better idea) -
The closed #185 had some bookkeeping fixes that look independent of the prefix caching issue. Would you consider splitting those out into a separate PR? I haven't verified them in detail yet, but they seem like useful prep work.
Contributor
Author
|
Sure. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This PR temporarily disables vLLM core prefix caching on Metal when paged attention is enabled.
As #185 's comments
Fixed #184