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

20
tests/lora/test_llama_tp.py
View File

@@ -186,25 +186,25 @@ def test_tp2_serialize_and_deserialize_lora(tmp_path, sql_lora_files,
model_uri = tmp_path / "vllm" / model_ref / suffix / model_name
tensorizer_config = TensorizerConfig(tensorizer_uri=str(model_uri))
loaded_vllm_model = LLM(model=model_ref,
load_format="tensorizer",
enable_lora=True,
enforce_eager=True,
model_loader_extra_config=tensorizer_config,
max_num_seqs=13,
tensor_parallel_size=2,
max_loras=2)
loaded_llm = LLM(model=model_ref,
load_format="tensorizer",
enable_lora=True,
enforce_eager=True,
model_loader_extra_config=tensorizer_config,
max_num_seqs=13,
tensor_parallel_size=2,
max_loras=2)
tc_as_dict = tensorizer_config.to_serializable()
print("lora adapter created")
assert do_sample(loaded_vllm_model,
assert do_sample(loaded_llm,
sql_lora_files,
tensorizer_config_dict=tc_as_dict,
lora_id=0) == EXPECTED_NO_LORA_OUTPUT
print("lora 1")
assert do_sample(loaded_vllm_model,
assert do_sample(loaded_llm,
sql_lora_files,
tensorizer_config_dict=tc_as_dict,
lora_id=1) == EXPECTED_LORA_OUTPUT