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

[Model] Always use Transformers backend for PaliGemma and Gemma3-MM (#26715)

Browse Source 
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
This commit is contained in:
Cyrus Leung
2025-10-17 13:03:35 +08:00
committed by GitHub
parent 9c2c2287a0
commit 8c017b3490
12 changed files with 54 additions and 1219 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
tests/models/language/generation/test_gemma.py
View File

@@ -3,7 +3,7 @@
import numpy as np
import pytest
MODELS = ["google/gemma-2b", "google/gemma-2-2b", "google/gemma-3-4b-it"]
MODELS = ["google/gemma-2b", "google/gemma-2-2b"]
@pytest.mark.parametrize("model", MODELS)
@@ -14,14 +14,8 @@ def test_dummy_loader(vllm_runner, monkeypatch, model: str) -> None:
model,
load_format="dummy",
) as llm:
if model == "google/gemma-3-4b-it":
normalizers = llm.llm.collective_rpc(
lambda self: self.model_runner.model.language_model.model.normalizer.cpu().item() # noqa: E501
)
config = llm.llm.llm_engine.model_config.hf_config.text_config
else:
normalizers = llm.llm.collective_rpc(
lambda self: self.model_runner.model.model.normalizer.cpu().item()
)
config = llm.llm.llm_engine.model_config.hf_config
normalizers = llm.apply_model(
lambda model: model.model.normalizer.cpu().item()
)
config = llm.llm.llm_engine.model_config.hf_config
assert np.allclose(normalizers, config.hidden_size**0.5, rtol=2e-3)