[CI/Build] Further decouple HuggingFace implementation from ours during tests #4166
Conversation
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
DarkLight1337
changed the title
|
OK the tests now pass. |
53 tasks
robertgshaw2-redhat
pushed a commit
to neuralmagic/nm-vllm
that referenced
this pull request
May 19, 2024
dtrifiro
pushed a commit
to dtrifiro/vllm
that referenced
this pull request
May 21, 2024
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Outdated suggestions cannot be applied.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.
Currently, the
HfRunnerused for model tests loads the tokenizer using ourget_tokenizermethod instead of directly through HuggingFace, resulting in possible overlap in the underlying implementation withVllmRunner. This PR usesAutoProcessor(falling back toAutoTokenizer) to load the tokenizer which better decouples the implementation.Similarly, this PR replaces our
_VISION_LANGUAGE_MODELSdictionary with HuggingFace's method to register VLMs so that they can be loaded withAutoModel.