Skip to content

[multimodal][test] Reduce memory utilization for test_siglip to avoid OOM #29504

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Dec 1, 2025
+7 −1
Merged

[multimodal][test] Reduce memory utilization for test_siglip to avoid OOM #29504

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f59b406
[multimodal][test] Reduce memory utilization for test_siglip to avoid…
zhxchen17 Nov 26, 2025
613ccd0
Merge branch 'main' into zhxchen17/torch_ci_oom_2
DarkLight1337 Nov 30, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 7 additions & 1 deletion tests/models/multimodal/pooling/test_siglip.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,7 +32,12 @@ def _run_test(
dtype: str,
) -> None:
with vllm_runner(
model, runner="pooling", dtype=dtype, enforce_eager=True, max_model_len=64
model,
runner="pooling",
dtype=dtype,
enforce_eager=True,
max_model_len=64,
gpu_memory_utilization=0.7,
) as vllm_model:
vllm_outputs = vllm_model.embed(input_texts, images=input_images)

Expand Down Expand Up @@ -129,6 +134,7 @@ def test_models_text_image_no_crash(
dtype=dtype,
enforce_eager=True,
max_model_len=64,
gpu_memory_utilization=0.7,
) as vllm_model:
with pytest.raises(ValueError, match="not both"):
vllm_model.embed(texts, images=images)
Expand Down