Skip to content

[Misc] Remove user-facing error for removed VLM args #9104

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Oct 6, 2024
Merged

[Misc] Remove user-facing error for removed VLM args #9104

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 0 additions & 4 deletions docs/source/models/vlm.rst
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -23,10 +23,6 @@ The :class:`~vllm.LLM` class can be instantiated in much the same way as languag

llm = LLM(model="llava-hf/llava-1.5-7b-hf")

.. note::
We have removed all vision language related CLI args in the ``0.5.1`` release. **This is a breaking change**, so please update your code to follow
the above snippet. Specifically, ``image_feature_size`` can no longer be specified as we now calculate that internally for each model.

To pass an image to the model, note the following in :class:`vllm.inputs.PromptType`:

* ``prompt``: The prompt should follow the format that is documented on HuggingFace.
Expand Down
10 changes: 1 addition & 9 deletions vllm/entrypoints/llm.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -180,15 +180,7 @@ def __init__(

if "disable_log_stats" not in kwargs:
kwargs["disable_log_stats"] = True
removed_vision_keys = (
"image_token_id",
"image_feature_size",
"image_input_shape",
"image_input_type",
)
if any(k in kwargs for k in removed_vision_keys):
raise TypeError(
"There is no need to pass vision-related arguments anymore.")

engine_args = EngineArgs(
model=model,
tokenizer=tokenizer,
Expand Down
Loading