Skip to content

[Bugfix] Fix OOM tests in initialization test #21921

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
vllm-bot merged 1 commit into from
Jul 30, 2025
Merged

[Bugfix] Fix OOM tests in initialization test #21921

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
14 changes: 8 additions & 6 deletions tests/models/test_initialization.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -33,12 +33,6 @@ def can_initialize(model_arch: str, monkeypatch: pytest.MonkeyPatch,
model_info.check_available_online(on_fail="skip")
model_info.check_transformers_version(on_fail="skip")

# FIXME: Possible memory leak in the previous tests?
if model_arch in ("Glm4vForConditionalGeneration",
"GraniteSpeechForConditionalGeneration",
"KimiVLForConditionalGeneration"):
pytest.skip("Avoid OOM")

if model_arch in ("Llama4ForCausalLM", "EagleLlama4ForCausalLM"):
from vllm.model_executor.models.llama4 import Llama4ForCausalLM
from vllm.model_executor.models.registry import ModelRegistry
Expand Down Expand Up @@ -87,6 +81,14 @@ def hf_overrides(hf_config: PretrainedConfig) -> PretrainedConfig:
"num_hidden_layers": 1,
})

# e.g.: Qwen/Qwen2-Audio-7B-Instruct
if hasattr(hf_config, "audio_config"):
hf_config.audio_config.update({
"num_layers": 1,
"num_hidden_layers": 1,
"encoder_layers": 1,
})

return hf_config

# Avoid calling model.forward()
Expand Down
1 change: 1 addition & 0 deletions vllm/model_executor/models/glm4_1v.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1275,6 +1275,7 @@ def __init__(self, *, vllm_config: VllmConfig, prefix: str = ""):
vllm_config=vllm_config,
prefix=maybe_prefix(prefix, ""),
architectures=["Glm4ForCausalLM"],
hf_config=self.config.get_text_config(),
)

self.make_empty_intermediate_tensors = (
Expand Down