handler.py

from transformers import Qwen2VLForConditionalGeneration, AutoTokenizer, AutoProcessor
from qwen_vl_utils import process_vision_info



class EndpointHandler():

    def __init__(self):
        # default: Load the model on the available device(s)
        self.model = Qwen2VLForConditionalGeneration.from_pretrained(
            "Qwen/Qwen2-VL-7B-Instruct", torch_dtype="auto", device_map="auto", 
        )

        # We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
        # model = Qwen2VLForConditionalGeneration.from_pretrained(
        #     "Qwen/Qwen2-VL-7B-Instruct",
        #     torch_dtype=torch.bfloat16,
        #     attn_implementation="flash_attention_2",
        #     device_map="auto",
        # )

        # default processer
        self.processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct")

        # The default range for the number of visual tokens per image in the model is 4-16384. You can set min_pixels and max_pixels according to your needs, such as a token count range of 256-1280, to balance speed and memory usage.
        # min_pixels = 256*28*28
        # max_pixels = 1280*28*28
        # processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)



    def __call__(self, data):

        text = self.processor.apply_chat_template(
            data["messages"], tokenize=False, add_generation_prompt=True
        )
        image_inputs, video_inputs = process_vision_info(data["messages"])

        inputs = self.processor(
            text=[text],
            images=image_inputs,
            videos=video_inputs,
            padding=True,
            return_tensors="pt",
        )

        inputs = inputs.to(self.model.device)

        # Inference: Generation of the output
        generated_ids = self.model.generate(**inputs, max_new_tokens=data.get("max_new_tokens", 128))
        generated_ids_trimmed = [
            out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
        ]
        output_text = self.processor.batch_decode(
            generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
        )
        return {
            "output": output_text,
        }