[VLM] Disallow overflowing max_model_len for multimodal models
#7998
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
53 tasks
|
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, please make sure to run full CI as it is required to merge (or just use auto-merge). To run full CI, you can do one of these:
🚀 |
DarkLight1337
added
the
ready
ywang96
approved these changes
Aug 29, 2024
Comment on lines
+1967
to
+1969
| "number of text tokens plus multimodal tokens. For image " | ||
| "inputs, the number of image tokens depends on the number " | ||
| "of images, and possibly their aspect ratios as well.") |
There was a problem hiding this comment.
Nit: we can probably just generalize the wording here for all multimodal data items instead of calling out image in particular, but we can do this change in a later PR.
Alvant
pushed a commit
to compressa-ai/vllm
that referenced
this pull request
Oct 26, 2024
…m-project#7998) Signed-off-by: Alvant <alvasian@yandex.ru>
LeiWang1999
pushed a commit
to LeiWang1999/vllm-bitblas
that referenced
this pull request
Mar 26, 2025
…m-project#7998) Signed-off-by: LeiWang1999 <leiwang1999@outlook.com>
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Outdated suggestions cannot be applied.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 placeholder tokens are silently truncated if they exceed the context length, causing confusing errors when later assigning multimodal features to the placeholder tokens inside the model. (e.g. #6176)
This PR avoids such problems by checking the length of the processed prompt beforehand.