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

[Frontend] Use engine argument to control MM cache size (#22441)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-08-08 00:47:10 +08:00
committed by GitHub
parent 8c9da6be22
commit 139d155781
13 changed files with 101 additions and 47 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
tests/models/multimodal/processing/test_llama4.py
View File

@@ -15,14 +15,14 @@ from ...utils import build_model_context
["meta-llama/Llama-4-Scout-17B-16E-Instruct"])
@pytest.mark.parametrize("mm_processor_kwargs", [{}])
@pytest.mark.parametrize("num_imgs", [1, 5])
@pytest.mark.parametrize("disable_mm_preprocessor_cache", [True, False])
@pytest.mark.parametrize("mm_processor_cache_gb", [0, 4])
@pytest.mark.parametrize("tokenized_prompt", [True, False])
def test_processor_override(
image_assets: ImageTestAssets,
model_id: str,
mm_processor_kwargs: dict,
num_imgs: int,
disable_mm_preprocessor_cache: bool,
mm_processor_cache_gb: int,
tokenized_prompt: bool,
):
"""Ensure llama4 processor works properly."""
@@ -30,7 +30,7 @@ def test_processor_override(
model_id,
mm_processor_kwargs=mm_processor_kwargs,
limit_mm_per_prompt={"image": num_imgs},
disable_mm_preprocessor_cache=disable_mm_preprocessor_cache,
mm_processor_cache_gb=mm_processor_cache_gb,
)
processor = MULTIMODAL_REGISTRY.create_processor(ctx.model_config)
config = processor.info.get_hf_config()