vllm/tests/models/decoder_only/vision_language/test_paligemma.py

import os
from typing import List, Optional, Tuple, Type

import pytest
from transformers import (AutoConfig, AutoModelForVision2Seq, AutoTokenizer,
                          BatchEncoding)

from vllm.multimodal.utils import rescale_image_size
from vllm.sequence import SampleLogprobs
from vllm.utils import STR_DTYPE_TO_TORCH_DTYPE, is_hip

from ....conftest import IMAGE_ASSETS, HfRunner, VllmRunner, _ImageAssets
from ...utils import check_logprobs_close

HF_IMAGE_PROMPTS = IMAGE_ASSETS.prompts({
    "stop_sign":
    "caption es",
    "cherry_blossom":
    "What is in the picture?",
})

models = ["google/paligemma-3b-mix-224"]

# ROCm Triton FA can run into compilation issues with these models due to,
# excessive use of shared memory. Use other backends in the meantime.
# FIXME (mattwong, gshtrasb, hongxiayan)
if is_hip():
    os.environ["VLLM_USE_TRITON_FLASH_ATTN"] = "0"


def vllm_to_hf_output(vllm_output: Tuple[List[int], str,
                                         Optional[SampleLogprobs]],
                      model: str):
    """Sanitize vllm output to be comparable with hf output."""
    output_ids, output_str, out_logprobs = vllm_output

    config = AutoConfig.from_pretrained(model)
    image_token_id = config.image_token_index

    tokenizer = AutoTokenizer.from_pretrained(model)
    eos_token_id = tokenizer.eos_token_id

    hf_output_ids = [
        token_id for idx, token_id in enumerate(output_ids)
        if token_id != image_token_id or output_ids[idx - 1] != image_token_id
    ]

    hf_output_str = output_str

    if hf_output_ids[-1] == eos_token_id:
        hf_output_str = hf_output_str + tokenizer.decode(eos_token_id)

    return hf_output_ids, hf_output_str, out_logprobs


def run_test(
    hf_runner: Type[HfRunner],
    vllm_runner: Type[VllmRunner],
    image_assets: _ImageAssets,
    model: str,
    *,
    size_factors: List[float],
    dtype: str,
    max_tokens: int,
    num_logprobs: int,
    tensor_parallel_size: int,
    distributed_executor_backend: Optional[str] = None,
):
    """Inference result should be the same between hf and vllm.

    All the image fixtures for the test are from IMAGE_ASSETS.
    For huggingface runner, we provide the PIL images as input.
    For vllm runner, we provide MultiModalDataDict objects 
    and corresponding MultiModalConfig as input.
    Note, the text input is also adjusted to abide by vllm contract.
    The text output is sanitized to be able to compare with hf.
    """
    torch_dtype = STR_DTYPE_TO_TORCH_DTYPE[dtype]
    images = [asset.pil_image for asset in image_assets]

    inputs_per_image = [(
        [prompt for _ in size_factors],
        [rescale_image_size(image, factor) for factor in size_factors],
    ) for image, prompt in zip(images, HF_IMAGE_PROMPTS)]

    # NOTE: take care of the order. run vLLM first, and then run HF.
    # vLLM needs a fresh new process without cuda initialization.
    # if we run HF first, the cuda initialization will be done and it
    # will hurt multiprocessing backend with fork method (the default method).

    # max_model_len should be greater than image_feature_size
    with vllm_runner(model,
                     dtype=dtype,
                     tensor_parallel_size=tensor_parallel_size,
                     distributed_executor_backend=distributed_executor_backend,
                     enforce_eager=True) as vllm_model:
        vllm_outputs_per_image = [
            vllm_model.generate_greedy_logprobs(prompts,
                                                max_tokens,
                                                num_logprobs=num_logprobs,
                                                images=images)
            for prompts, images in inputs_per_image
        ]

    def process(hf_inputs: BatchEncoding):
        hf_inputs["pixel_values"] = hf_inputs["pixel_values"] \
            .to(torch_dtype)  # type: ignore
        return hf_inputs

    with hf_runner(model,
                   dtype=dtype,
                   postprocess_inputs=process,
                   auto_cls=AutoModelForVision2Seq) as hf_model:
        hf_outputs_per_image = [
            hf_model.generate_greedy_logprobs_limit(prompts,
                                                    max_tokens,
                                                    num_logprobs=num_logprobs,
                                                    images=images)
            for prompts, images in inputs_per_image
        ]

    for hf_outputs, vllm_outputs in zip(hf_outputs_per_image,
                                        vllm_outputs_per_image):

        check_logprobs_close(
            outputs_0_lst=hf_outputs,
            outputs_1_lst=[
                vllm_to_hf_output(vllm_output, model)
                for vllm_output in vllm_outputs
            ],
            name_0="hf",
            name_1="vllm",
        )


@pytest.mark.parametrize("model", models)
@pytest.mark.parametrize(
    "size_factors",
    [
        # No image
        [],
        # Single-scale
        [1.0],
        # Single-scale, batched
        [1.0, 1.0, 1.0],
        # Multi-scale
        [0.25, 0.5, 1.0],
    ],
)
@pytest.mark.parametrize("dtype", [
    pytest.param(
        "float",
        marks=pytest.mark.skipif(
            is_hip(),
            reason=
            "ROCm FA does not yet fully support 32-bit precision on PaliGemma")
    ), "half"
])
@pytest.mark.parametrize("max_tokens", [128])
@pytest.mark.parametrize("num_logprobs", [5])
def test_models(hf_runner, vllm_runner, image_assets, model, size_factors,
                dtype: str, max_tokens: int, num_logprobs: int) -> None:
    run_test(
        hf_runner,
        vllm_runner,
        image_assets,
        model,
        size_factors=size_factors,
        dtype=dtype,
        max_tokens=max_tokens,
        num_logprobs=num_logprobs,
        tensor_parallel_size=1,
    )