[Mistral] Fix query scaling for Mistral4 and Ministral3#44860
Merged
Cyrilvallez merged 1 commit intomainfrom Mar 19, 2026
Merged
[Mistral] Fix query scaling for Mistral4 and Ministral3#44860Cyrilvallez merged 1 commit intomainfrom
Cyrilvallez merged 1 commit intomainfrom
Conversation
Contributor
|
[For maintainers] Suggested jobs to run (before merge) run-slow: ministral3, mistral4 |
|
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update. |
Cyrilvallez
force-pushed
the
fix-mistral
branch
from
98dcbc2 to
c396876
Compare
ArthurZucker
approved these changes
Mar 19, 2026
Collaborator
ArthurZucker
left a comment
ArthurZucker
left a comment
There was a problem hiding this comment.
Can you run integration tests please ? 😉
Member
Author
|
Well, I expect this to break (at least some of) the integration tests, so let's wait to hear back from @juliendenize and @patrickvonplaten if it's correct instead! |
Member
Author
|
run-slow: ministral3, mistral4 |
Contributor
|
This comment contains models: ["models/ministral3", "models/mistral4"] |
Contributor
|
Thanks !! |
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
4 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do?
As per the title. As discussed offline with the Mistral team, the scaling applied to the query should not be the absolute one (old
cache_position), but the actualposition_ids, taking into account padding, packed format in case of continuous batching etc