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

[Model] Add PaddleOCR-VL Model Support (#27758)

Browse Source 
Signed-off-by: zhangyue <zhangyue66@baidu.com>
Signed-off-by: Roger Wang <hey@rogerw.io>
Signed-off-by: Isotr0py <mozf@mail2.sysu.edu.cn>
Signed-off-by: zhangyue66 <zhangyue66@baidu.com>
Co-authored-by: Roger Wang <hey@rogerw.io>
Co-authored-by: Isotr0py <mozf@mail2.sysu.edu.cn>
This commit is contained in:
zhang-prog
2025-11-03 19:04:22 +08:00
committed by GitHub
parent 32257297dd
commit 40b69e33e7
7 changed files with 1475 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
examples/offline_inference/vision_language_multi_image.py
View File

@@ -801,6 +801,27 @@ def load_ovis2_5(question: str, image_urls: list[str]) -> ModelRequestData:
)
def load_paddleocr_vl(question: str, image_urls: list[str]) -> ModelRequestData:
model_name = "PaddlePaddle/PaddleOCR-VL"
engine_args = EngineArgs(
model=model_name,
trust_remote_code=True,
max_model_len=8192,
max_num_seqs=2,
limit_mm_per_prompt={"image": len(image_urls)},
)
placeholders = "<|IMAGE_START|><|IMAGE_PLACEHOLDER|><|IMAGE_END|>" * len(image_urls)
prompt = f"<|begin_of_sentence|>User: {question}{placeholders}\nAssistant: "
return ModelRequestData(
engine_args=engine_args,
prompt=prompt,
image_data=[fetch_image(url) for url in image_urls],
)
def load_pixtral_hf(question: str, image_urls: list[str]) -> ModelRequestData:
model_name = "mistral-community/pixtral-12b"
@@ -1312,6 +1333,7 @@ model_example_map = {
"NVLM_D": load_nvlm_d,
"ovis": load_ovis,
"ovis2_5": load_ovis2_5,
"paddleocr_vl": load_paddleocr_vl,
"phi3_v": load_phi3v,
"phi4_mm": load_phi4mm,
"phi4_multimodal": load_phi4_multimodal,