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

10
tests/model_executor/test_model_load_with_params.py
View File

@@ -32,8 +32,8 @@ def test_model_loading_with_params(vllm_runner):
output = vllm_model.embed("Write a short story about a robot that"
" dreams for the first time.\n")
model_config = vllm_model.model.llm_engine.model_config
model_tokenizer = vllm_model.model.llm_engine.tokenizer
model_config = vllm_model.llm.llm_engine.model_config
model_tokenizer = vllm_model.llm.llm_engine.tokenizer
# asserts on the bert model config file
assert model_config.encoder_config["max_seq_length"] == 512
@@ -70,8 +70,8 @@ def test_roberta_model_loading_with_params(vllm_runner):
output = vllm_model.embed("Write a short story about a robot that"
" dreams for the first time.\n")
model_config = vllm_model.model.llm_engine.model_config
model_tokenizer = vllm_model.model.llm_engine.tokenizer
model_config = vllm_model.llm.llm_engine.model_config
model_tokenizer = vllm_model.llm.llm_engine.tokenizer
# asserts on the bert model config file
assert model_config.encoder_config["max_seq_length"] == 512
@@ -108,7 +108,7 @@ def test_facebook_roberta_model_loading_with_params(vllm_runner):
output = vllm_model.embed("Write a short story about a robot that"
" dreams for the first time.\n")
model_tokenizer = vllm_model.model.llm_engine.tokenizer
model_tokenizer = vllm_model.llm.llm_engine.tokenizer
assert model_tokenizer.tokenizer_id == model_name
def check_model(model):