biondizzle/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 2 Packages Projects Releases Wiki Activity

[Doc] Convert Sphinx directives ( {class}, {meth}, {attr}, ...) to MkDocs format for better documentation linking (#18663)

Browse Source 
Signed-off-by: Zerohertz <ohg3417@gmail.com>
This commit is contained in:
Hyogeun Oh (오효근)
2025-05-27 17:44:20 +09:00
committed by GitHub
parent 6881107948
commit a68e293cb9
37 changed files with 360 additions and 247 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
vllm/model_executor/models/qwen_vl.py
View File

@@ -382,7 +382,8 @@ def _get_tokenizer_without_image_pad(
tokenizer: PreTrainedTokenizer) -> PreTrainedTokenizer:
"""
The logic of adding image pad tokens should only be applied in
{class}`QwenVLProcessor`, so they are patched out here.
[`QwenVLProcessor`][vllm.model_executor.models.qwen_vl.QwenVLProcessor],
so they are patched out here.
The definition of the wrapped tokenizer can be found here:
https://huggingface.co/Qwen/Qwen-VL/blob/main/tokenization_qwen.py