tokenizer: return successful mlx-lm load result#215
Open
krystophny wants to merge 2 commits intowaybarrios:mainfrom
Open
tokenizer: return successful mlx-lm load result#215krystophny wants to merge 2 commits intowaybarrios:mainfrom
krystophny wants to merge 2 commits intowaybarrios:mainfrom
Conversation
krystophny
changed the title
Thump604
approved these changes
Mar 25, 2026
Collaborator
Thump604
left a comment
Thump604
left a comment
There was a problem hiding this comment.
Good catch — the mlx-lm fallback path was silently returning None. The regression test is a nice touch. +1
This was referenced Mar 25, 2026
krystophny
added a commit
to computor-org/vllm-mlx
that referenced
this pull request
Mar 25, 2026
Add test confirming deduplicated terminal blocks correctly isolate recurrent state per sequence. Remove the duplicate tokenizer return fix that already ships in PR waybarrios#215.
krystophny
added a commit
to computor-org/vllm-mlx
that referenced
this pull request
Mar 26, 2026
Add test confirming deduplicated terminal blocks correctly isolate recurrent state per sequence. Remove the duplicate tokenizer return fix that already ships in PR waybarrios#215.
krystophny
added a commit
to computor-org/vllm-mlx
that referenced
this pull request
Mar 26, 2026
krystophny
added a commit
to computor-org/vllm-mlx
that referenced
this pull request
Mar 26, 2026
Add test confirming deduplicated terminal blocks correctly isolate recurrent state per sequence. Remove the duplicate tokenizer return fix that already ships in PR waybarrios#215.
krystophny
added a commit
to computor-org/vllm-mlx
that referenced
this pull request
Mar 26, 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
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.
Summary
load_model_with_fallback()so a successfulmlx_lm.load()returns(model, tokenizer)instead of falling through asNoneMain files
vllm_mlx/utils/tokenizer.pytests/test_tokenizer_utils.pyReviewer focus
The bug is small but user-visible: a valid MLX load can succeed internally and still surface as a failed startup because the successful tuple is not returned.
Tests
PYTHONPATH=/Users/ert/code/vllm-mlx /Users/ert/code/.venv/bin/python -m pytest tests/test_tokenizer_utils.py -qpython3 -m compileall vllm_mlx