fix mtp prefix cache flag#824
Merged
Merged
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
This PR aims to automatically disable prefix caching when using certain MTP speculative draft models that don’t support it, preventing incorrect cache behavior.
Changes:
- Detect speculative draft model
model_typefor Qwen MTP variants. - If prefix caching is enabled for unsupported MTP draft models, emit a warning and disable prefix caching automatically.
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
Comment on lines
+1015
to
+1017
| spec_model_type = getattr( | ||
| self.speculative_config.hf_config, "model_type", None | ||
| ) |
jiayyu
force-pushed
the
fpz/fix_prefix_default_on
branch
from
92d1d1e to
48c0b21
Compare
valarLip
approved these changes
May 18, 2026
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Technical Details
Test Plan
Test Result
Submission Checklist