adding head dim since 3.2 has it - #1244
Merged
Merged
Conversation
meta-cla
Bot
added
the
CLA Signed
cbalioglu
approved these changes
Aug 8, 2025
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What does this PR do? Please describe:
Our llama config does not have the head dim since we compute it dynamically and default 8B / 70B models didnt have it in HG configs too. However, smaller 3.2 models introduced it so we must save head dim in HG config in order to override the default head dim that is 128.
Prior to this fix the vllm loading of 1B model didnt work due to config bug.