xinyun/vllm
1
0
Fork 0
mirror of https://git.datalinker.icu/vllm-project/vllm.git synced 2025-12-17 07:25:01 +08:00
Code Issues Packages Projects Releases Wiki Activity

[Misc] unify variable for LLM instance v2 (#21356)

Browse Source 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
This commit is contained in:
Ning Xie 2025-07-22 21:32:36 +08:00 committed by GitHub
parent ed25054577
commit 0df4d9b06b
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
tests/models/language/generation/test_gemma.py
View File

@ -15,13 +15,13 @@ def test_dummy_loader(vllm_runner, monkeypatch, model: str) -> None:
load_format="dummy", load_format="dummy",
) as llm: ) as llm:
if model == "google/gemma-3-4b-it": if model == "google/gemma-3-4b-it":
normalizers = llm.model.collective_rpc( normalizers = llm.llm.collective_rpc(
lambda self: self.model_runner.model.language_model.model. lambda self: self.model_runner.model.language_model.model.
normalizer.cpu().item()) normalizer.cpu().item())
config = llm.model.llm_engine.model_config.hf_config.text_config config = llm.llm.llm_engine.model_config.hf_config.text_config
else: else:
normalizers = llm.model.collective_rpc( normalizers = llm.llm.collective_rpc(
lambda self: self.model_runner.model.model.normalizer.cpu( lambda self: self.model_runner.model.model.normalizer.cpu(
).item()) ).item())
config = llm.model.llm_engine.model_config.hf_config config = llm.llm.llm_engine.model_config.hf_config
assert np.allclose(normalizers, config.hidden_size**0.5, rtol=2e-3) assert np.allclose(normalizers, config.hidden_size**0.5, rtol=2e-3)