Microsoft Harrier OSS support - #58
Open
kyr0 wants to merge 1 commit into
Open
Conversation
Author
|
Anyways, you can test this PR with this in a few copy & paste commands :)
make test-embed EMBED_TEXT="mlx-embedding is such a cool project" |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 change adds support for Microsoft Harrier OSS by implementing a more generic code path for gemma3_text embeddings that doesn't require dense heads. This PR is meant to be challenged strongly by you @Blaizzy please :) We know each other from my last MLX audio patch that eventually got merged. This time I'm not sure if this generic solution would still be compatible with all other Gemma 3 embedding model type variants. Do we have any e2e/integration tests? I'd love to see projects like this having a Makefile where you simply do:
make e2eand it runs thru all models, downloads them one by one, drops them again, and runs inference per-model. Only this way we could get 100% certainty that every code change does well. Not sure but we have Github Actions with macOS runners. Maybe we can even automate this...?