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

[Misc] unify variable for LLM instance (#20996)

Browse Source 
Signed-off-by: Andy Xie <andy.xning@gmail.com>
This commit is contained in:
Ning Xie
2025-07-21 19:18:33 +08:00
committed by GitHub
parent e6b90a2805
commit d97841078b
53 changed files with 237 additions and 236 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/quantization/test_gptq_dynamic.py
View File

@@ -39,7 +39,7 @@ def test_gptq_with_dynamic(vllm_runner, model_id: str, use_marlin_kernel: bool,
linear_method_cls = GPTQMarlinLinearMethod if use_marlin_kernel else (
GPTQLinearMethod)
for name, submodule in (vllm_model.model.llm_engine.model_executor.
for name, submodule in (vllm_model.llm.llm_engine.model_executor.
driver_worker.model_runner.model.named_modules()):
if name == "lm_head":
assert isinstance(submodule.quant_method, linear_method_cls)