20231088/vllm
1
0
Fork 0
Code Issues Pull Requests Actions 1 Packages Projects Releases Wiki Activity

[Misc] Clean up processor tests (#14771)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung 2025-03-14 02:25:37 +08:00 committed by GitHub
parent 01b3fd0af7
commit 8e9ffd37d6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
8 changed files with 30 additions and 46 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
tests/models/multimodal/processing/test_h2ovl.py
View File

@ -96,14 +96,14 @@ def _run_check(
tokenizer = processor.info.get_tokenizer()
config = processor.info.get_hf_config()
prompt = "<image>" * len(images)
mm_data = {"image": images}
total_expected_num_patches = sum(
_get_expected_num_patches(config, image, len(images), min_num, max_num)
for image in images)
processed_inputs = processor.apply("<image>" * len(images), mm_data,
mm_processor_kwargs)
processed_inputs = processor.apply(prompt, mm_data, mm_processor_kwargs)
# Ensure we have the right number of placeholders per num_crops size
image_token_id = tokenizer.convert_tokens_to_ids("<IMG_CONTEXT>")
@ -152,9 +152,7 @@ def test_processor_override(
}
ctx = build_model_context(
model_name=model_id,
tokenizer_name=model_id,
trust_remote_code=True,
model_id,
mm_processor_kwargs=mm_processor_kwargs if kwargs_on_init else None,
limit_mm_per_prompt={"image": len(size_factors)},
)

10
tests/models/multimodal/processing/test_idefics3.py
View File

@ -9,10 +9,8 @@ from vllm.transformers_utils.tokenizer import cached_tokenizer_from_config
from ....conftest import _ImageAssets
from ...utils import build_model_context
models = ["HuggingFaceM4/Idefics3-8B-Llama3"]
@pytest.mark.parametrize("model", models)
@pytest.mark.parametrize("model_id", ["HuggingFaceM4/Idefics3-8B-Llama3"])
# yapf: disable
@pytest.mark.parametrize(
("mm_processor_kwargs", "expected_toks_per_img"),
@ -25,7 +23,7 @@ models = ["HuggingFaceM4/Idefics3-8B-Llama3"]
@pytest.mark.parametrize("kwargs_on_init", [True, False])
def test_processor_override(
image_assets: _ImageAssets,
model: str,
model_id: str,
mm_processor_kwargs: dict[str, object],
expected_toks_per_img: int,
num_imgs: int,
@ -36,9 +34,7 @@ def test_processor_override(
# in this test and assume that the kwargs will be correctly expanded by
# the partial when calling the custom input processor.
ctx = build_model_context(
model_name=model,
tokenizer_name=model,
trust_remote_code=True,
model_id,
mm_processor_kwargs=mm_processor_kwargs if kwargs_on_init else None,
limit_mm_per_prompt={"image": num_imgs},
)

8
tests/models/multimodal/processing/test_internvl.py
View File

@ -56,14 +56,14 @@ def _run_check(
tokenizer = processor.info.get_tokenizer()
config = processor.info.get_hf_config()
prompt = "<image>" * len(images)
mm_data = {"image": images}
total_expected_num_patches = sum(
_get_expected_num_patches(config, image, len(images), min_num, max_num)
for image in images)
processed_inputs = processor.apply("<image>" * len(images), mm_data,
mm_processor_kwargs)
processed_inputs = processor.apply(prompt, mm_data, mm_processor_kwargs)
# Ensure we have the right number of placeholders per num_crops size
image_token_id = tokenizer.convert_tokens_to_ids("<IMG_CONTEXT>")
@ -109,9 +109,7 @@ def test_processor_override(
}
ctx = build_model_context(
model_name=model_id,
tokenizer_name=model_id,
trust_remote_code=True,
model_id,
mm_processor_kwargs=mm_processor_kwargs if kwargs_on_init else None,
limit_mm_per_prompt={"image": len(size_factors)},
)

9
tests/models/multimodal/processing/test_llava_next.py
View File

@ -36,8 +36,7 @@ def _validate_image_max_tokens_one(
@pytest.mark.parametrize("model_id", ["llava-hf/llava-v1.6-mistral-7b-hf"])
def test_processor_max_tokens(model_id):
ctx = build_model_context(
model_name=model_id,
tokenizer_name=model_id,
model_id,
mm_processor_kwargs=None,
limit_mm_per_prompt={"image": 1},
)
@ -136,8 +135,7 @@ def _test_image_prompt_replacements(
@pytest.mark.parametrize("num_imgs", [1, 2])
def test_processor_prompt_replacements_regression(model_id, num_imgs):
ctx = build_model_context(
model_name=model_id,
tokenizer_name=model_id,
model_id,
mm_processor_kwargs=None,
limit_mm_per_prompt={"image": num_imgs},
)
@ -166,8 +164,7 @@ def test_processor_prompt_replacements_regression(model_id, num_imgs):
@pytest.mark.parametrize("num_imgs", [1])
def test_processor_prompt_replacements_all(model_id, num_imgs):
ctx = build_model_context(
model_name=model_id,
tokenizer_name=model_id,
model_id,
mm_processor_kwargs=None,
limit_mm_per_prompt={"image": num_imgs},
)

9
tests/models/multimodal/processing/test_llava_onevision.py
View File

@ -37,8 +37,7 @@ def _validate_image_max_tokens_one(
["llava-hf/llava-onevision-qwen2-0.5b-ov-hf"])
def test_processor_max_tokens(model_id):
ctx = build_model_context(
model_name=model_id,
tokenizer_name=model_id,
model_id,
mm_processor_kwargs=None,
limit_mm_per_prompt={"image": 1},
)
@ -136,8 +135,7 @@ def _test_image_prompt_replacements(
@pytest.mark.parametrize("num_imgs", [1, 2])
def test_processor_prompt_replacements_regression(model_id, num_imgs):
ctx = build_model_context(
model_name=model_id,
tokenizer_name=model_id,
model_id,
mm_processor_kwargs=None,
limit_mm_per_prompt={"image": num_imgs},
)
@ -167,8 +165,7 @@ def test_processor_prompt_replacements_regression(model_id, num_imgs):
@pytest.mark.parametrize("num_imgs", [1])
def test_processor_prompt_replacements_all(model_id, num_imgs):
ctx = build_model_context(
model_name=model_id,
tokenizer_name=model_id,
model_id,
mm_processor_kwargs=None,
limit_mm_per_prompt={"image": num_imgs},
)

4
tests/models/multimodal/processing/test_phi3v.py
View File

@ -35,9 +35,7 @@ def test_processor_override(
from vllm.model_executor.models.phi3v import _IMAGE_TOKEN_ID
ctx = build_model_context(
model_name=model_id,
tokenizer_name=model_id,
trust_remote_code=True,
model_id,
mm_processor_kwargs=mm_processor_kwargs if kwargs_on_init else None,
limit_mm_per_prompt={"image": num_imgs},
)

3
tests/models/multimodal/processing/test_qwen2_vl.py
View File

@ -30,8 +30,7 @@ def test_processor_override(
):
"""Ensure Qwen2VLMultiModalProcessor handles min/max pixels properly."""
ctx = build_model_context(
model_name=model_id,
tokenizer_name=model_id,
model_id,
mm_processor_kwargs=mm_processor_kwargs if kwargs_on_init else None,
limit_mm_per_prompt={"image": num_imgs},
)

25
tests/models/utils.py
View File

@ -10,6 +10,8 @@ from vllm.config import ModelConfig, TaskOption
from vllm.inputs import InputContext
from vllm.sequence import Logprob, PromptLogprobs, SampleLogprobs
from .registry import HF_EXAMPLE_MODELS
TokensText = tuple[list[int], str]
@ -250,10 +252,8 @@ def check_logprobs_close(
def build_model_context(
model_name: str,
model_id: str,
task: TaskOption = "auto",
tokenizer_name: Optional[str] = None,
trust_remote_code: bool = False,
dtype: Optional[Union[str, torch.dtype]] = None,
mm_processor_kwargs: Optional[dict] = None,
limit_mm_per_prompt: Optional[dict] = None,
@ -262,9 +262,7 @@ def build_model_context(
"""Creates an InputContext for a given model.
Args:
model_name: Name of the model being considered.
tokenizer_name: Name of the tokenizer being considered.
trust_remote_code: Whether or not to allow loading remote code.
model_id: ID of the model being considered.
mm_processor_kwargs: optional processor kwargs for to be leveraged
in the input processor, mapper, dummy data creation, etc.
limit_mm_per_prompt: Multimodal limits.
@ -272,21 +270,24 @@ def build_model_context(
Returns:
InputContext for the model being considered.
"""
if tokenizer_name is None:
tokenizer_name = model_name
model_info = HF_EXAMPLE_MODELS.find_hf_info(model_id)
model_info.check_available_online(on_fail="skip")
model_info.check_transformers_version(on_fail="skip")
if dtype is None:
dtype = "half"
model_config = ModelConfig(
model_name,
model_id,
task=task,
tokenizer=tokenizer_name,
tokenizer_mode="auto",
trust_remote_code=trust_remote_code,
tokenizer=model_info.tokenizer or model_id,
tokenizer_mode=model_info.tokenizer_mode,
trust_remote_code=model_info.trust_remote_code,
dtype=dtype,
seed=0,
mm_processor_kwargs=mm_processor_kwargs,
limit_mm_per_prompt=limit_mm_per_prompt,
disable_mm_preprocessor_cache=disable_mm_preprocessor_cache,
hf_overrides=model_info.hf_overrides,
)
return InputContext(model_config)