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

6
tests/models/language/pooling/test_truncation_control.py
View File

@@ -28,7 +28,7 @@ def test_smaller_truncation_size(vllm_runner,
with vllm_runner(model_name, task="embed",
max_model_len=max_model_len) as vllm_model:
vllm_output = vllm_model.model.encode(
vllm_output = vllm_model.llm.encode(
input_str, truncate_prompt_tokens=truncate_prompt_tokens)
prompt_tokens = vllm_output[0].prompt_token_ids
@@ -43,7 +43,7 @@ def test_max_truncation_size(vllm_runner,
with vllm_runner(model_name, task="embed",
max_model_len=max_model_len) as vllm_model:
vllm_output = vllm_model.model.encode(
vllm_output = vllm_model.llm.encode(
input_str, truncate_prompt_tokens=truncate_prompt_tokens)
prompt_tokens = vllm_output[0].prompt_token_ids
@@ -61,7 +61,7 @@ def test_bigger_truncation_size(vllm_runner,
model_name, task="embed",
max_model_len=max_model_len) as vllm_model:
llm_output = vllm_model.model.encode(
llm_output = vllm_model.llm.encode(
input_str, truncate_prompt_tokens=truncate_prompt_tokens)
assert llm_output == f"""truncate_prompt_tokens value