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

4
tests/quantization/test_quark.py
View File

@@ -107,11 +107,11 @@ def test_quark_fp8_parity(vllm_runner):
}
with (vllm_runner(quark_model_id, **llm_kwargs) as
quark_handle, vllm_runner(fp8_model_id, **llm_kwargs) as fp8_handle):
quark_model = (quark_handle.model.llm_engine.model_executor.
quark_model = (quark_handle.llm.llm_engine.model_executor.
driver_worker.model_runner.model)
quark_state_dict = quark_model.state_dict()
fp8_model = (fp8_handle.model.llm_engine.model_executor.driver_worker.
fp8_model = (fp8_handle.llm.llm_engine.model_executor.driver_worker.
model_runner.model)
fp8_state_dict = fp8_model.state_dict()